Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.7567. Min Act: -0.1700
Data Index: 6705576 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.7255. Min Act: -0.1700
Data Index: 5990151 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.4755. Min Act: -0.1700
Data Index: 4888501 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.4755. Min Act: -0.1700
Data Index: 6844009 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.3505. Min Act: -0.1700
Data Index: 3152542 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.3192. Min Act: -0.1700
Data Index: 1924046 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3386882 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.2567. Min Act: -0.1700
Data Index: 6932604 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.2567. Min Act: -0.1700
Data Index: 2381644 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.2567. Min Act: -0.1700
Data Index: 1115379 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1942. Min Act: -0.1700
Data Index: 6343978 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1942. Min Act: -0.1700
Data Index: 8731283 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1630. Min Act: -0.1700
Data Index: 3765256 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1630. Min Act: -0.1700
Data Index: 5522579 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1630. Min Act: -0.1700
Data Index: 8738506 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1317. Min Act: -0.1700
Data Index: 2845170 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1317. Min Act: -0.1700
Data Index: 6737574 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1005. Min Act: -0.1700
Data Index: 3848559 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1005. Min Act: -0.1700
Data Index: 5877649 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7567. Min Range: -5.7567
Max Act: 5.1005. Min Act: -0.1700
Data Index: 5218970 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19