Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.8736. Min Act: -0.1700
Data Index: 6528424 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.9361. Min Act: -0.1700
Data Index: 3604776 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.9361. Min Act: -0.1700
Data Index: 4123321 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.8736. Min Act: -0.1700
Data Index: 1791569 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.8111. Min Act: -0.1700
Data Index: 6348092 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.7486. Min Act: -0.1700
Data Index: 2846186 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6861. Min Act: -0.1700
Data Index: 4745128 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6861. Min Act: -0.1700
Data Index: 6195972 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6861. Min Act: -0.1700
Data Index: 1209570 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6548. Min Act: -0.1700
Data Index: 5410072 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6548. Min Act: -0.1700
Data Index: 5040075 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6236. Min Act: -0.1700
Data Index: 2243713 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.6236. Min Act: -0.1700
Data Index: 6136187 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.5923. Min Act: -0.1700
Data Index: 8503864 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.5923. Min Act: -0.1700
Data Index: 1780746 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.5611. Min Act: -0.1700
Data Index: 8273941 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.5298. Min Act: -0.1700
Data Index: 513141 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.5298. Min Act: -0.1700
Data Index: 4123123 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.5298. Min Act: -0.1700
Data Index: 2722362 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9361. Min Range: -7.9361
Max Act: 7.4986. Min Act: -0.1700
Data Index: 5470994 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19