Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 88 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.8910. Min Act: -0.1700
Data Index: 1038693 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.8598. Min Act: -0.1700
Data Index: 3990940 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.7348. Min Act: -0.1700
Data Index: 3234572 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.6098. Min Act: -0.1700
Data Index: 3284821 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.6098. Min Act: -0.1700
Data Index: 53963 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.5160. Min Act: -0.1700
Data Index: 3284824 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.5160. Min Act: -0.1700
Data Index: 3104822 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4848. Min Act: -0.1700
Data Index: 2574233 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4535. Min Act: -0.1700
Data Index: 3586293 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4535. Min Act: -0.1700
Data Index: 1139556 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4535. Min Act: -0.1700
Data Index: 2501969 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4848. Min Act: -0.1700
Data Index: 4990105 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4535. Min Act: -0.1700
Data Index: 3585967 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4535. Min Act: -0.1700
Data Index: 707842 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4223. Min Act: -0.1700
Data Index: 4987577 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.3910. Min Act: -0.1700
Data Index: 8606212 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4223. Min Act: -0.1700
Data Index: 2268329 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.3910. Min Act: -0.1700
Data Index: 1582299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.4223. Min Act: -0.1700
Data Index: 1507133 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8910. Min Range: -6.8910
Max Act: 6.3910. Min Act: -0.1700
Data Index: 3428674 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19