Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3348. Min Range: -5.3348
Max Act: 5.3348. Min Act: -0.1700
Data Index: 734412 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.9911. Min Act: -0.1700
Data Index: 1300466 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.9911. Min Act: -0.1700
Data Index: 6480118 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.9911. Min Act: -0.1700
Data Index: 1993780 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.9598. Min Act: -0.1700
Data Index: 3049825 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.9286. Min Act: -0.1700
Data Index: 5987496 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8973. Min Act: -0.1700
Data Index: 595589 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8661. Min Act: -0.1700
Data Index: 4226434 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8661. Min Act: -0.1700
Data Index: 6408620 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8661. Min Act: -0.1700
Data Index: 1684109 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8973. Min Act: -0.1700
Data Index: 1306255 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8348. Min Act: -0.1700
Data Index: 1872715 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8348. Min Act: -0.1700
Data Index: 1548431 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8036. Min Act: -0.1700
Data Index: 6008748 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.8348. Min Act: -0.1700
Data Index: 7783567 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.7723. Min Act: -0.1700
Data Index: 6757573 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.7723. Min Act: -0.1700
Data Index: 4021804 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.7411. Min Act: -0.1700
Data Index: 290587 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.7098. Min Act: -0.1700
Data Index: 4158648 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3348. Min Range: -5.3348
Max Act: 4.7098. Min Act: -0.1700
Data Index: 5267938 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19