Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1361. Min Range: -9.1361
Max Act: 9.1361. Min Act: -0.1700
Data Index: 5292098 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1361. Min Range: -9.1361
Max Act: 9.0111. Min Act: -0.1700
Data Index: 7983402 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.7611. Min Act: -0.1700
Data Index: 3090576 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.6986. Min Act: -0.1700
Data Index: 2802647 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.5736. Min Act: -0.1700
Data Index: 3742492 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.5736. Min Act: -0.1700
Data Index: 2829906 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.5111. Min Act: -0.1700
Data Index: 8699096 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.3861. Min Act: -0.1700
Data Index: 2655242 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.3861. Min Act: -0.1700
Data Index: 7583002 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.3236. Min Act: -0.1700
Data Index: 5881649 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.3236. Min Act: -0.1700
Data Index: 378309 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.3236. Min Act: -0.1700
Data Index: 3784299 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.3236. Min Act: -0.1700
Data Index: 2763142 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.2611. Min Act: -0.1700
Data Index: 8589677 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.2611. Min Act: -0.1700
Data Index: 6104127 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 434771 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 7040919 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 4355870 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 8398722 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1361. Min Range: -9.1361
Max Act: 8.1986. Min Act: -0.1700
Data Index: 2382254 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19