Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3865 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1546. Min Range: -6.1546
Max Act: 6.1546. Min Act: -0.1700
Data Index: 2893733 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1546. Min Range: -6.1546
Max Act: 6.0296. Min Act: -0.1700
Data Index: 7965284 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.9359. Min Act: -0.1700
Data Index: 3286867 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.8734. Min Act: -0.1700
Data Index: 4901906 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.8109. Min Act: -0.1700
Data Index: 2654606 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.8109. Min Act: -0.1700
Data Index: 4290162 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.8109. Min Act: -0.1700
Data Index: 895814 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.8109. Min Act: -0.1700
Data Index: 7752116 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7796. Min Act: -0.1700
Data Index: 6616273 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7796. Min Act: -0.1700
Data Index: 907104 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7796. Min Act: -0.1700
Data Index: 8787692 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7796. Min Act: -0.1700
Data Index: 2247067 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7171. Min Act: -0.1700
Data Index: 7978651 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7484. Min Act: -0.1700
Data Index: 8517236 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7484. Min Act: -0.1700
Data Index: 4699972 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.7171. Min Act: -0.1700
Data Index: 8008031 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.6859. Min Act: -0.1700
Data Index: 6894434 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.6859. Min Act: -0.1700
Data Index: 8051939 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.6546. Min Act: -0.1700
Data Index: 370958 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1546. Min Range: -6.1546
Max Act: 5.6546. Min Act: -0.1700
Data Index: 2889867 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19