Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.3379. Min Act: -0.1700
Data Index: 1610482 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.3379. Min Act: -0.1700
Data Index: 1798065 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.3065. Min Act: -0.1700
Data Index: 75351 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.2908. Min Act: -0.1700
Data Index: 4196167 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.2594. Min Act: -0.1700
Data Index: 4239634 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.2594. Min Act: -0.1700
Data Index: 5420758 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.2437. Min Act: -0.1700
Data Index: 7012116 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.2437. Min Act: -0.1700
Data Index: 7746189 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1965. Min Act: -0.1700
Data Index: 908438 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1965. Min Act: -0.1700
Data Index: 2516506 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1650. Min Act: -0.1700
Data Index: 1773146 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1336. Min Act: -0.1700
Data Index: 7971224 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1336. Min Act: -0.1700
Data Index: 8006419 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1178. Min Act: -0.1700
Data Index: 7783780 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1336. Min Act: -0.1700
Data Index: 6488511 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1178. Min Act: -0.1700
Data Index: 6808430 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1021. Min Act: -0.1700
Data Index: 6111655 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.1178. Min Act: -0.1700
Data Index: 4636232 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.0863. Min Act: -0.1700
Data Index: 6548395 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3379. Min Range: -3.3379
Max Act: 3.0863. Min Act: -0.1700
Data Index: 1195472 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19