Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.8431. Min Act: -0.1700
Data Index: 2250573 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.6244. Min Act: -0.1700
Data Index: 8754243 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5931. Min Act: -0.1700
Data Index: 5070740 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5931. Min Act: -0.1700
Data Index: 956911 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5306. Min Act: -0.1700
Data Index: 5331732 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5619. Min Act: -0.1700
Data Index: 956915 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5619. Min Act: -0.1700
Data Index: 1940644 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5306. Min Act: -0.1700
Data Index: 6128833 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5306. Min Act: -0.1700
Data Index: 7377490 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5306. Min Act: -0.1700
Data Index: 1873137 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.5306. Min Act: -0.1700
Data Index: 611793 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4994. Min Act: -0.1700
Data Index: 8532490 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4681. Min Act: -0.1700
Data Index: 3526011 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4994. Min Act: -0.1700
Data Index: 1206788 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4681. Min Act: -0.1700
Data Index: 7834837 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4369. Min Act: -0.1700
Data Index: 3828529 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4369. Min Act: -0.1700
Data Index: 8358124 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4369. Min Act: -0.1700
Data Index: 7979468 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4369. Min Act: -0.1700
Data Index: 8683599 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8431. Min Range: -5.8431
Max Act: 5.4681. Min Act: -0.1700
Data Index: 3831464 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19