Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1120 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4265. Min Range: -4.4265
Max Act: 4.4265. Min Act: -0.1700
Data Index: 3792272 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4265. Min Range: -4.4265
Max Act: 4.0515. Min Act: -0.1700
Data Index: 4079527 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4265. Min Range: -4.4265
Max Act: 4.0202. Min Act: -0.1700
Data Index: 8694642 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4265. Min Range: -4.4265
Max Act: 4.0202. Min Act: -0.1700
Data Index: 6125895 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.9264. Min Act: -0.1700
Data Index: 5804728 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.9264. Min Act: -0.1700
Data Index: 5158879 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5663272 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8952. Min Act: -0.1700
Data Index: 971433 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 2784068 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 2130224 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 3634130 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 6827808 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 2215892 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 150359 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 2664652 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8639. Min Act: -0.1700
Data Index: 8068190 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8483. Min Act: -0.1700
Data Index: 4249681 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8483. Min Act: -0.1700
Data Index: 3870002 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8483. Min Act: -0.1700
Data Index: 3663287 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4265. Min Range: -4.4265
Max Act: 3.8483. Min Act: -0.1700
Data Index: 6242166 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19