Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0306. Min Range: -7.0306
Max Act: 7.0306. Min Act: -0.1700
Data Index: 4880927 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0306. Min Range: -7.0306
Max Act: 7.0306. Min Act: -0.1700
Data Index: 2327484 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.9994. Min Act: -0.1700
Data Index: 4011669 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0306. Min Range: -7.0306
Max Act: 7.0306. Min Act: -0.1700
Data Index: 6546737 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.9369. Min Act: -0.1700
Data Index: 5089206 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.9369. Min Act: -0.1700
Data Index: 7095522 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.9369. Min Act: -0.1700
Data Index: 6992162 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8744. Min Act: -0.1700
Data Index: 5757504 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.8431. Min Act: -0.1700
Data Index: 5420889 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7806. Min Act: -0.1700
Data Index: 8118881 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7494. Min Act: -0.1700
Data Index: 8249524 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7806. Min Act: -0.1700
Data Index: 959877 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7494. Min Act: -0.1700
Data Index: 3292425 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.7181. Min Act: -0.1700
Data Index: 1305886 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6869. Min Act: -0.1700
Data Index: 6587417 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6869. Min Act: -0.1700
Data Index: 8117700 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6556. Min Act: -0.1700
Data Index: 2663075 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6244. Min Act: -0.1700
Data Index: 696762 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.6556. Min Act: -0.1700
Data Index: 4237884 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0306. Min Range: -7.0306
Max Act: 6.5931. Min Act: -0.1700
Data Index: 4815147 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19