Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3465. Min Range: -6.3465
Max Act: 6.3465. Min Act: -0.1700
Data Index: 2940735 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3465. Min Range: -6.3465
Max Act: 6.2528. Min Act: -0.1700
Data Index: 1841624 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3465. Min Range: -6.3465
Max Act: 6.1590. Min Act: -0.1700
Data Index: 4158929 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3465. Min Range: -6.3465
Max Act: 6.0340. Min Act: -0.1700
Data Index: 2247758 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.9715. Min Act: -0.1700
Data Index: 6346361 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.9403. Min Act: -0.1700
Data Index: 3743945 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.9403. Min Act: -0.1700
Data Index: 1435117 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.9090. Min Act: -0.1700
Data Index: 6271406 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8465. Min Act: -0.1700
Data Index: 5707124 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8778. Min Act: -0.1700
Data Index: 7282783 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8465. Min Act: -0.1700
Data Index: 730225 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8153. Min Act: -0.1700
Data Index: 6803877 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8465. Min Act: -0.1700
Data Index: 385140 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8153. Min Act: -0.1700
Data Index: 1032519 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8153. Min Act: -0.1700
Data Index: 1848663 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8153. Min Act: -0.1700
Data Index: 6529087 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.8153. Min Act: -0.1700
Data Index: 6773931 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.7840. Min Act: -0.1700
Data Index: 1628594 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.7840. Min Act: -0.1700
Data Index: 235468 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3465. Min Range: -6.3465
Max Act: 5.7840. Min Act: -0.1700
Data Index: 5115130 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19