Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5473 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.7933. Min Act: -0.1700
Data Index: 2588595 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.7933. Min Act: -0.1700
Data Index: 7268922 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.7621. Min Act: -0.1700
Data Index: 4207961 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.6996. Min Act: -0.1700
Data Index: 3033730 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.6683. Min Act: -0.1700
Data Index: 8806839 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.6683. Min Act: -0.1700
Data Index: 4167363 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.6683. Min Act: -0.1700
Data Index: 886253 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.6371. Min Act: -0.1700
Data Index: 4554103 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.6371. Min Act: -0.1700
Data Index: 2835845 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.5746. Min Act: -0.1700
Data Index: 3993443 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.5121. Min Act: -0.1700
Data Index: 6355148 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4808. Min Act: -0.1700
Data Index: 7459888 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4808. Min Act: -0.1700
Data Index: 3813530 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.5121. Min Act: -0.1700
Data Index: 2474654 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4808. Min Act: -0.1700
Data Index: 1646433 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4808. Min Act: -0.1700
Data Index: 868403 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4808. Min Act: -0.1700
Data Index: 133116 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4808. Min Act: -0.1700
Data Index: 7832888 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4496. Min Act: -0.1700
Data Index: 4228475 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7933. Min Range: -5.7933
Max Act: 5.4496. Min Act: -0.1700
Data Index: 2252389 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19