Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5525 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0230. Min Range: -5.0230
Max Act: 5.0230. Min Act: -0.1700
Data Index: 1061758 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7730. Min Act: -0.1700
Data Index: 7147631 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7418. Min Act: -0.1700
Data Index: 1247585 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6480. Min Act: -0.1700
Data Index: 2191092 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6480. Min Act: -0.1700
Data Index: 4848687 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6168. Min Act: -0.1700
Data Index: 7435829 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.5543. Min Act: -0.1700
Data Index: 1111898 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.5543. Min Act: -0.1700
Data Index: 1697430 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.5230. Min Act: -0.1700
Data Index: 6712639 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4605. Min Act: -0.1700
Data Index: 106656 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4605. Min Act: -0.1700
Data Index: 5955860 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.3980. Min Act: -0.1700
Data Index: 5657873 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 7998039 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 7519192 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 5190262 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 4991804 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 496312 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 6780843 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.4293. Min Act: -0.1700
Data Index: 2198698 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.3980. Min Act: -0.1700
Data Index: 2511684 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19