Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4753 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9462. Min Range: -9.9462
Max Act: 9.9462. Min Act: -0.1700
Data Index: 3507641 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9462. Min Range: -9.9462
Max Act: 9.5087. Min Act: -0.1700
Data Index: 5511483 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9462. Min Range: -9.9462
Max Act: 9.3212. Min Act: -0.1700
Data Index: 6032505 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9462. Min Range: -9.9462
Max Act: 9.3212. Min Act: -0.1700
Data Index: 6853158 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9462. Min Range: -9.9462
Max Act: 9.0712. Min Act: -0.1700
Data Index: 8336388 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9462. Min Range: -9.9462
Max Act: 9.0087. Min Act: -0.1700
Data Index: 4757963 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.9462. Min Act: -0.1700
Data Index: 7000289 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8837. Min Act: -0.1700
Data Index: 5965301 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8837. Min Act: -0.1700
Data Index: 2687660 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8212. Min Act: -0.1700
Data Index: 8690888 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8212. Min Act: -0.1700
Data Index: 1349862 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8212. Min Act: -0.1700
Data Index: 562969 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8212. Min Act: -0.1700
Data Index: 36359 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.8212. Min Act: -0.1700
Data Index: 7527653 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.7587. Min Act: -0.1700
Data Index: 5842635 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.6962. Min Act: -0.1700
Data Index: 2399848 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.7587. Min Act: -0.1700
Data Index: 3053692 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.7587. Min Act: -0.1700
Data Index: 3414990 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.6962. Min Act: -0.1700
Data Index: 3082296 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9462. Min Range: -9.9462
Max Act: 8.6962. Min Act: -0.1700
Data Index: 3899228 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19