Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4005 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.8848. Min Act: -0.1700
Data Index: 4315726 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.8536. Min Act: -0.1700
Data Index: 3658003 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.7598. Min Act: -0.1700
Data Index: 5523119 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6973. Min Act: -0.1700
Data Index: 6220481 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6661. Min Act: -0.1700
Data Index: 7366930 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6348. Min Act: -0.1700
Data Index: 2800966 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.5411. Min Act: -0.1700
Data Index: 4514329 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4786. Min Act: -0.1700
Data Index: 4828244 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4473. Min Act: -0.1700
Data Index: 6832348 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4786. Min Act: -0.1700
Data Index: 1675689 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4161. Min Act: -0.1700
Data Index: 6137030 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.3536. Min Act: -0.1700
Data Index: 5036208 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.3848. Min Act: -0.1700
Data Index: 3495423 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.3848. Min Act: -0.1700
Data Index: 6615695 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4161. Min Act: -0.1700
Data Index: 3130043 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.3848. Min Act: -0.1700
Data Index: 5610182 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.3536. Min Act: -0.1700
Data Index: 3607077 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.2598. Min Act: -0.1700
Data Index: 3412143 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2457873 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2004993 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19