Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.8191. Min Act: -0.1700
Data Index: 3108320 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7566. Min Act: -0.1700
Data Index: 5082082 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7566. Min Act: -0.1699
Data Index: 1176958 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7566. Min Act: -0.1700
Data Index: 427731 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 1049669 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7566. Min Act: -0.1700
Data Index: 3604856 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 6765063 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 996449 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 999994 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 1919804 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 1903356 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1929785 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 1359422 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6941. Min Act: -0.1700
Data Index: 4253453 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6941. Min Act: -0.1700
Data Index: 6490087 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1245487 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6941. Min Act: -0.1700
Data Index: 5429504 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6628. Min Act: -0.1699
Data Index: 2512660 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1575986 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8191. Min Range: -4.8191
Max Act: 4.7253. Min Act: -0.1700
Data Index: 534959 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19