Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.5902. Min Act: -0.1700
Data Index: 4507218 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.5590. Min Act: -0.1700
Data Index: 6306263 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.4965. Min Act: -0.1700
Data Index: 3966043 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.5277. Min Act: -0.1700
Data Index: 3653293 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.4340. Min Act: -0.1700
Data Index: 3732819 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.4027. Min Act: -0.1700
Data Index: 4012897 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.4027. Min Act: -0.1700
Data Index: 1960092 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.4027. Min Act: -0.1700
Data Index: 5814771 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3715. Min Act: -0.1700
Data Index: 5408564 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3715. Min Act: -0.1700
Data Index: 5542404 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3402. Min Act: -0.1700
Data Index: 1548227 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3715. Min Act: -0.1700
Data Index: 2366773 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3402. Min Act: -0.1700
Data Index: 4973610 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3090. Min Act: -0.1700
Data Index: 1371336 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3090. Min Act: -0.1700
Data Index: 660353 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3090. Min Act: -0.1700
Data Index: 6387051 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.2777. Min Act: -0.1700
Data Index: 4319158 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3090. Min Act: -0.1700
Data Index: 7460037 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3090. Min Act: -0.1700
Data Index: 5832412 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5902. Min Range: -4.5902
Max Act: 4.3090. Min Act: -0.1700
Data Index: 2238772 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19