Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.5475. Min Act: -0.1700
Data Index: 2733623 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.5162. Min Act: -0.1700
Data Index: 4299466 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4535. Min Act: -0.1700
Data Index: 5122159 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4535. Min Act: -0.1700
Data Index: 1906230 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4379. Min Act: -0.1700
Data Index: 6201259 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4222. Min Act: -0.1700
Data Index: 5199314 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3908. Min Act: -0.1700
Data Index: 283737 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4065. Min Act: -0.1700
Data Index: 7833631 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4065. Min Act: -0.1700
Data Index: 116752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4065. Min Act: -0.1700
Data Index: 7645602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.4065. Min Act: -0.1700
Data Index: 3834196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3908. Min Act: -0.1700
Data Index: 858937 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3752. Min Act: -0.1700
Data Index: 244702 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3752. Min Act: -0.1700
Data Index: 2668428 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3595. Min Act: -0.1700
Data Index: 5126746 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3595. Min Act: -0.1700
Data Index: 8118032 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3438. Min Act: -0.1700
Data Index: 5018407 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3124. Min Act: -0.1700
Data Index: 5289034 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3281. Min Act: -0.1700
Data Index: 6413629 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5475. Min Range: -3.5475
Max Act: 3.3281. Min Act: -0.1700
Data Index: 2755232 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19