Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5196 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3434. Min Range: -6.3434
Max Act: 6.3434. Min Act: -0.1700
Data Index: 7720173 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3434. Min Range: -6.3434
Max Act: 6.0934. Min Act: -0.1700
Data Index: 2147788 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3434. Min Range: -6.3434
Max Act: 6.0622. Min Act: -0.1700
Data Index: 8544492 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3434. Min Range: -6.3434
Max Act: 6.0309. Min Act: -0.1700
Data Index: 1280840 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9997. Min Act: -0.1700
Data Index: 5114683 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9684. Min Act: -0.1700
Data Index: 4836826 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9997. Min Act: -0.1700
Data Index: 2601770 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9684. Min Act: -0.1700
Data Index: 4781924 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9372. Min Act: -0.1700
Data Index: 4974755 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9372. Min Act: -0.1700
Data Index: 6328569 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9059. Min Act: -0.1700
Data Index: 3503698 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9059. Min Act: -0.1700
Data Index: 5337133 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9059. Min Act: -0.1700
Data Index: 14548 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9059. Min Act: -0.1700
Data Index: 3073723 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.9059. Min Act: -0.1700
Data Index: 2655880 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.8747. Min Act: -0.1700
Data Index: 3769659 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.8747. Min Act: -0.1700
Data Index: 8117918 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.8434. Min Act: -0.1700
Data Index: 4714753 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.8122. Min Act: -0.1700
Data Index: 634383 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3434. Min Range: -6.3434
Max Act: 5.8122. Min Act: -0.1700
Data Index: 971308 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19