Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.5664. Min Act: -0.1700
Data Index: 1675560 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.5664. Min Act: -0.1700
Data Index: 3379220 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.5664. Min Act: -0.1700
Data Index: 577058 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.4727. Min Act: -0.1700
Data Index: 925236 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.4727. Min Act: -0.1700
Data Index: 2312848 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.4414. Min Act: -0.1700
Data Index: 530978 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.4102. Min Act: -0.1700
Data Index: 6557008 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.4102. Min Act: -0.1700
Data Index: 3584163 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.4102. Min Act: -0.1700
Data Index: 3283017 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6175694 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.3164. Min Act: -0.1700
Data Index: 3687382 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.3477. Min Act: -0.1700
Data Index: 7190062 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.3477. Min Act: -0.1700
Data Index: 3126356 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6264760 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.2852. Min Act: -0.1700
Data Index: 4844551 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.2539. Min Act: -0.1700
Data Index: 803031 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.2227. Min Act: -0.1700
Data Index: 3433804 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.2539. Min Act: -0.1700
Data Index: 7662372 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.2227. Min Act: -0.1700
Data Index: 8563925 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5664. Min Range: -6.5664
Max Act: 6.2539. Min Act: -0.1700
Data Index: 5805395 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19