Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1956 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2193. Min Range: -7.2193
Max Act: 7.2193. Min Act: -0.1700
Data Index: 5973191 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2193. Min Range: -7.2193
Max Act: 7.1256. Min Act: -0.1700
Data Index: 8514477 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2193. Min Range: -7.2193
Max Act: 7.0006. Min Act: -0.1700
Data Index: 7913078 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.8443. Min Act: -0.1700
Data Index: 2452150 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.8443. Min Act: -0.1700
Data Index: 1150849 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.8131. Min Act: -0.1700
Data Index: 3363773 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7818. Min Act: -0.1700
Data Index: 2302422 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7506. Min Act: -0.1700
Data Index: 5631542 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7193. Min Act: -0.1700
Data Index: 5586657 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6881. Min Act: -0.1700
Data Index: 3553100 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 3694561 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 6907141 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 5735510 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 5657500 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 8493612 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 7957072 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.5943. Min Act: -0.1700
Data Index: 4583509 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.5318. Min Act: -0.1700
Data Index: 3545860 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.5318. Min Act: -0.1700
Data Index: 6383401 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.5006. Min Act: -0.1700
Data Index: 1179829 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19