Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.9037. Min Act: -0.1700
Data Index: 1023338 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.9037. Min Act: -0.1700
Data Index: 5150252 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8724. Min Act: -0.1700
Data Index: 6261165 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 2794736 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8412. Min Act: -0.1700
Data Index: 2583408 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8412. Min Act: -0.1700
Data Index: 5003183 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 5651603 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 6592588 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 5758121 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 2097345 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 2877875 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.8099. Min Act: -0.1700
Data Index: 802649 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7787. Min Act: -0.1700
Data Index: 3064258 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7787. Min Act: -0.1700
Data Index: 9833 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7474. Min Act: -0.1700
Data Index: 3052421 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7474. Min Act: -0.1700
Data Index: 2207545 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7474. Min Act: -0.1700
Data Index: 6041210 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7474. Min Act: -0.1700
Data Index: 4863021 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7474. Min Act: -0.1700
Data Index: 3920280 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9037. Min Range: -4.9037
Max Act: 4.7474. Min Act: -0.1700
Data Index: 8204969 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19