Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 704 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.2965. Min Act: -0.1700
Data Index: 1868736 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1402. Min Act: -0.1700
Data Index: 1868737 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1715. Min Act: -0.1700
Data Index: 1868735 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0152. Min Act: -0.1700
Data Index: 7746009 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.9840. Min Act: -0.1700
Data Index: 8816835 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.9527. Min Act: -0.1700
Data Index: 597959 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8902. Min Act: -0.1700
Data Index: 7472989 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8902. Min Act: -0.1700
Data Index: 3647106 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8590. Min Act: -0.1700
Data Index: 8242976 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8590. Min Act: -0.1700
Data Index: 5459078 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8277. Min Act: -0.1700
Data Index: 8660807 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8277. Min Act: -0.1700
Data Index: 1910313 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8277. Min Act: -0.1700
Data Index: 4179871 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.8277. Min Act: -0.1700
Data Index: 7232754 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.7965. Min Act: -0.1700
Data Index: 4437616 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.7965. Min Act: -0.1700
Data Index: 1499634 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.7652. Min Act: -0.1700
Data Index: 513597 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.7652. Min Act: -0.1700
Data Index: 3791296 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.7652. Min Act: -0.1700
Data Index: 8162066 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.7652. Min Act: -0.1700
Data Index: 6075429 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19