Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1321. Min Range: -5.1321
Max Act: 5.1321. Min Act: -0.1700
Data Index: 7129729 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1321. Min Range: -5.1321
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6682151 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1321. Min Range: -5.1321
Max Act: 5.0384. Min Act: -0.1700
Data Index: 1521573 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1321. Min Range: -5.1321
Max Act: 5.0071. Min Act: -0.1700
Data Index: 2598499 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.9134. Min Act: -0.1700
Data Index: 3906104 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.9134. Min Act: -0.1700
Data Index: 4382386 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7571. Min Act: -0.1700
Data Index: 7498046 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7571. Min Act: -0.1700
Data Index: 2413059 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7571. Min Act: -0.1700
Data Index: 8046224 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7259. Min Act: -0.1700
Data Index: 7608066 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7571. Min Act: -0.1700
Data Index: 212146 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7884. Min Act: -0.1700
Data Index: 1112138 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7571. Min Act: -0.1700
Data Index: 1060994 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7259. Min Act: -0.1700
Data Index: 3951113 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7259. Min Act: -0.1700
Data Index: 3758593 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7259. Min Act: -0.1700
Data Index: 4228460 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7259. Min Act: -0.1700
Data Index: 4421769 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.7571. Min Act: -0.1700
Data Index: 5436309 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.6946. Min Act: -0.1700
Data Index: 6228945 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1321. Min Range: -5.1321
Max Act: 4.6946. Min Act: -0.1700
Data Index: 6157326 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19