Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.5230. Min Act: -0.1700
Data Index: 3597436 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.4605. Min Act: -0.1700
Data Index: 6125603 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.4293. Min Act: -0.1700
Data Index: 529663 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.4293. Min Act: -0.1700
Data Index: 4281902 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3980. Min Act: -0.1700
Data Index: 1327682 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3980. Min Act: -0.1700
Data Index: 3351270 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3980. Min Act: -0.1700
Data Index: 5808109 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3980. Min Act: -0.1700
Data Index: 4132603 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3980. Min Act: -0.1700
Data Index: 1855067 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3668. Min Act: -0.1700
Data Index: 6369926 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3668. Min Act: -0.1700
Data Index: 3098701 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3668. Min Act: -0.1700
Data Index: 410667 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3668. Min Act: -0.1700
Data Index: 3948490 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3668. Min Act: -0.1700
Data Index: 3849346 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3043. Min Act: -0.1700
Data Index: 8609594 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3355. Min Act: -0.1700
Data Index: 3967018 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3355. Min Act: -0.1700
Data Index: 3597437 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3355. Min Act: -0.1700
Data Index: 7510847 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3043. Min Act: -0.1700
Data Index: 7235053 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5230. Min Range: -5.5230
Max Act: 5.3355. Min Act: -0.1700
Data Index: 1093028 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19