Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2083 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.7575. Min Act: -0.1700
Data Index: 8232725 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.6950. Min Act: -0.1700
Data Index: 6874056 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.6950. Min Act: -0.1700
Data Index: 3389374 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.6325. Min Act: -0.1700
Data Index: 4130127 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.6325. Min Act: -0.1700
Data Index: 6132975 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5700. Min Act: -0.1700
Data Index: 3255413 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5700. Min Act: -0.1700
Data Index: 666365 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5075. Min Act: -0.1700
Data Index: 6415382 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5075. Min Act: -0.1700
Data Index: 5631735 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5075. Min Act: -0.1700
Data Index: 5774373 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5075. Min Act: -0.1700
Data Index: 8789405 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.5075. Min Act: -0.1700
Data Index: 5153952 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.4450. Min Act: -0.1700
Data Index: 6172395 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.4450. Min Act: -0.1700
Data Index: 5489721 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.4450. Min Act: -0.1700
Data Index: 8594048 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.3825. Min Act: -0.1700
Data Index: 7566794 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.3825. Min Act: -0.1700
Data Index: 3625829 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.3825. Min Act: -0.1700
Data Index: 3793358 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.3825. Min Act: -0.1700
Data Index: 917334 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7575. Min Range: -9.7575
Max Act: 9.3825. Min Act: -0.1700
Data Index: 1866357 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19