Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1899. Min Range: -6.1899
Max Act: 6.1899. Min Act: -0.1700
Data Index: 3418623 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1899. Min Range: -6.1899
Max Act: 6.1899. Min Act: -0.1700
Data Index: 327911 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1899. Min Range: -6.1899
Max Act: 6.1587. Min Act: -0.1700
Data Index: 4080285 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1899. Min Range: -6.1899
Max Act: 6.0024. Min Act: -0.1700
Data Index: 2374201 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.9399. Min Act: -0.1700
Data Index: 1008790 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.9087. Min Act: -0.1700
Data Index: 2095841 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8774. Min Act: -0.1700
Data Index: 327913 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8774. Min Act: -0.1700
Data Index: 886980 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8774. Min Act: -0.1700
Data Index: 1342107 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8774. Min Act: -0.1700
Data Index: 1056013 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8462. Min Act: -0.1700
Data Index: 8535153 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8462. Min Act: -0.1700
Data Index: 1825817 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8462. Min Act: -0.1700
Data Index: 2907929 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8462. Min Act: -0.1700
Data Index: 3897180 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8774. Min Act: -0.1700
Data Index: 5633239 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.8149. Min Act: -0.1700
Data Index: 2775225 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.7837. Min Act: -0.1700
Data Index: 3418628 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.7837. Min Act: -0.1700
Data Index: 8056103 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.7837. Min Act: -0.1700
Data Index: 5529913 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1899. Min Range: -6.1899
Max Act: 5.7837. Min Act: -0.1700
Data Index: 986453 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19