Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4591 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.5421. Min Act: -0.1700
Data Index: 297634 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.3546. Min Act: -0.1700
Data Index: 5695078 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.3546. Min Act: -0.1700
Data Index: 3481986 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.3233. Min Act: -0.1700
Data Index: 113839 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.3233. Min Act: -0.1700
Data Index: 3461595 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2921. Min Act: -0.1700
Data Index: 5837359 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2921. Min Act: -0.1700
Data Index: 113840 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2608. Min Act: -0.1700
Data Index: 6814550 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2608. Min Act: -0.1700
Data Index: 6623472 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2608. Min Act: -0.1700
Data Index: 6164817 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2296. Min Act: -0.1700
Data Index: 4548486 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2296. Min Act: -0.1700
Data Index: 3112580 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2296. Min Act: -0.1700
Data Index: 7480236 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2296. Min Act: -0.1700
Data Index: 7977544 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.1983. Min Act: -0.1700
Data Index: 8177900 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.2296. Min Act: -0.1700
Data Index: 6685150 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.1983. Min Act: -0.1700
Data Index: 1085162 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.1983. Min Act: -0.1700
Data Index: 2149524 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.1983. Min Act: -0.1700
Data Index: 5818803 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5421. Min Range: -4.5421
Max Act: 4.1983. Min Act: -0.1700
Data Index: 2559690 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19