Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6247. Min Range: -9.6247
Max Act: 9.6247. Min Act: -0.1700
Data Index: 1297419 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.9997. Min Act: -0.1700
Data Index: 947803 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6247. Min Range: -9.6247
Max Act: 9.0622. Min Act: -0.1700
Data Index: 5195592 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.8747. Min Act: -0.1700
Data Index: 3445301 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.8122. Min Act: -0.1700
Data Index: 4859428 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.8122. Min Act: -0.1700
Data Index: 8045049 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.7497. Min Act: -0.1700
Data Index: 8528218 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.7497. Min Act: -0.1700
Data Index: 3631602 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6872. Min Act: -0.1700
Data Index: 1146699 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6872. Min Act: -0.1700
Data Index: 5428488 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6872. Min Act: -0.1700
Data Index: 1617281 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6247. Min Act: -0.1700
Data Index: 1297604 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6247. Min Act: -0.1700
Data Index: 8532459 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6247. Min Act: -0.1700
Data Index: 6437513 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6247. Min Act: -0.1700
Data Index: 4565612 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6872. Min Act: -0.1700
Data Index: 7916327 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.5622. Min Act: -0.1700
Data Index: 6790116 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6247. Min Act: -0.1700
Data Index: 4200201 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.5622. Min Act: -0.1700
Data Index: 5241194 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6247. Min Range: -9.6247
Max Act: 8.6247. Min Act: -0.1700
Data Index: 4366493 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19