Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.7244. Min Act: -0.1700
Data Index: 2060193 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5994. Min Act: -0.1700
Data Index: 6639433 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.6306. Min Act: -0.1700
Data Index: 3865410 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5994. Min Act: -0.1700
Data Index: 3375846 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5056. Min Act: -0.1700
Data Index: 1823655 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5056. Min Act: -0.1700
Data Index: 4437725 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4744. Min Act: -0.1700
Data Index: 3393026 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 1532461 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4431. Min Act: -0.1700
Data Index: 1066064 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4431. Min Act: -0.1700
Data Index: 7266364 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 1035587 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 5750519 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 2448280 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 7576827 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3806. Min Act: -0.1700
Data Index: 7833100 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 1092356 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3806. Min Act: -0.1700
Data Index: 3285046 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3806. Min Act: -0.1700
Data Index: 5074776 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3494. Min Act: -0.1700
Data Index: 317458 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3494. Min Act: -0.1700
Data Index: 239757 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19