Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 509 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.7898. Min Act: -0.1700
Data Index: 3049256 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.6648. Min Act: -0.1700
Data Index: 2463297 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.6335. Min Act: -0.1700
Data Index: 5255194 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.5398. Min Act: -0.1700
Data Index: 2026495 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.5398. Min Act: -0.1700
Data Index: 7152102 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.5398. Min Act: -0.1700
Data Index: 8451426 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.5085. Min Act: -0.1700
Data Index: 1963602 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.5085. Min Act: -0.1700
Data Index: 1687054 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.4772. Min Act: -0.1700
Data Index: 2687355 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.4772. Min Act: -0.1700
Data Index: 7353819 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.4147. Min Act: -0.1700
Data Index: 2320599 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.4460. Min Act: -0.1700
Data Index: 7514869 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.4147. Min Act: -0.1700
Data Index: 2746758 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.4147. Min Act: -0.1700
Data Index: 1068172 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.3835. Min Act: -0.1700
Data Index: 8224352 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.3522. Min Act: -0.1700
Data Index: 1505294 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.3522. Min Act: -0.1700
Data Index: 2905945 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.3522. Min Act: -0.1700
Data Index: 3145036 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.3835. Min Act: -0.1700
Data Index: 6304612 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7898. Min Range: -4.7898
Max Act: 4.3210. Min Act: -0.1700
Data Index: 3113910 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19