Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3498. Min Range: -7.3498
Max Act: 7.3498. Min Act: -0.1700
Data Index: 4747661 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3498. Min Range: -7.3498
Max Act: 7.3498. Min Act: -0.1700
Data Index: 2428102 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3498. Min Range: -7.3498
Max Act: 7.0686. Min Act: -0.1700
Data Index: 4443357 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3498. Min Range: -7.3498
Max Act: 7.0373. Min Act: -0.1700
Data Index: 7187333 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.9748. Min Act: -0.1700
Data Index: 2812791 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.9436. Min Act: -0.1700
Data Index: 7694420 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.9748. Min Act: -0.1700
Data Index: 3367381 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.9123. Min Act: -0.1700
Data Index: 3523703 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.8811. Min Act: -0.1700
Data Index: 2475286 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7873. Min Act: -0.1700
Data Index: 2352040 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7873. Min Act: -0.1700
Data Index: 5603459 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7873. Min Act: -0.1700
Data Index: 5658007 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7561. Min Act: -0.1700
Data Index: 6558848 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.6936. Min Act: -0.1700
Data Index: 8723591 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7561. Min Act: -0.1700
Data Index: 3561580 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7248. Min Act: -0.1700
Data Index: 1208957 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.6936. Min Act: -0.1700
Data Index: 5566963 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.7248. Min Act: -0.1700
Data Index: 5357938 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.6936. Min Act: -0.1700
Data Index: 3652758 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3498. Min Range: -7.3498
Max Act: 6.6623. Min Act: -0.1700
Data Index: 7567081 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19