Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.8701. Min Range: -12.8701
Max Act: 12.8701. Min Act: -0.1700
Data Index: 6640071 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8701. Min Range: -12.8701
Max Act: 12.3701. Min Act: -0.1700
Data Index: 1811335 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8701. Min Range: -12.8701
Max Act: 12.0576. Min Act: -0.1700
Data Index: 8530258 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8701. Min Range: -12.8701
Max Act: 12.1201. Min Act: -0.1700
Data Index: 230070 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.9326. Min Act: -0.1700
Data Index: 2789620 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8701. Min Range: -12.8701
Max Act: 12.1201. Min Act: -0.1700
Data Index: 1101453 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.9326. Min Act: -0.1700
Data Index: 480637 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.9326. Min Act: -0.1700
Data Index: 7242325 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.8701. Min Act: -0.1700
Data Index: 3130570 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.8701. Min Act: -0.1700
Data Index: 4671559 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.8076. Min Act: -0.1700
Data Index: 1413247 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.8701. Min Act: -0.1700
Data Index: 2438124 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.6201. Min Act: -0.1700
Data Index: 4431670 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.6201. Min Act: -0.1700
Data Index: 3227722 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.6826. Min Act: -0.1700
Data Index: 2630294 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.7451. Min Act: -0.1700
Data Index: 5069815 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.7451. Min Act: -0.1700
Data Index: 2577327 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.6201. Min Act: -0.1700
Data Index: 810316 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.6201. Min Act: -0.1700
Data Index: 7148423 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8701. Min Range: -12.8701
Max Act: 11.6201. Min Act: -0.1700
Data Index: 893374 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19