Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1604 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.9628. Min Act: -0.1700
Data Index: 6879489 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.9628. Min Act: -0.1700
Data Index: 3064313 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.9003. Min Act: -0.1700
Data Index: 8293815 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.8691. Min Act: -0.1700
Data Index: 4262111 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.8691. Min Act: -0.1700
Data Index: 8081342 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.8691. Min Act: -0.1700
Data Index: 5805193 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.8378. Min Act: -0.1700
Data Index: 3125474 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.8691. Min Act: -0.1700
Data Index: 6047692 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.8066. Min Act: -0.1700
Data Index: 6437140 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.7753. Min Act: -0.1700
Data Index: 4616942 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.7753. Min Act: -0.1700
Data Index: 8477321 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.7128. Min Act: -0.1700
Data Index: 8393990 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.7128. Min Act: -0.1700
Data Index: 8547762 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6816. Min Act: -0.1700
Data Index: 8410781 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6816. Min Act: -0.1700
Data Index: 1473661 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6816. Min Act: -0.1700
Data Index: 100008 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6503. Min Act: -0.1700
Data Index: 211009 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6503. Min Act: -0.1700
Data Index: 6613369 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6503. Min Act: -0.1700
Data Index: 1969666 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9628. Min Range: -4.9628
Max Act: 4.6503. Min Act: -0.1700
Data Index: 8059861 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19