Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4615. Min Range: -8.4615
Max Act: 8.4615. Min Act: -0.1700
Data Index: 2657904 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4615. Min Range: -8.4615
Max Act: 8.0240. Min Act: -0.1700
Data Index: 1702832 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.7740. Min Act: -0.1700
Data Index: 7184784 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6803. Min Act: -0.1700
Data Index: 353537 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6490. Min Act: -0.1700
Data Index: 8452229 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6490. Min Act: -0.1700
Data Index: 5931448 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6178. Min Act: -0.1700
Data Index: 3524389 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6178. Min Act: -0.1700
Data Index: 3595461 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6178. Min Act: -0.1700
Data Index: 8746489 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.6178. Min Act: -0.1700
Data Index: 2653468 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.5553. Min Act: -0.1700
Data Index: 6936493 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.5553. Min Act: -0.1700
Data Index: 1888290 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.5553. Min Act: -0.1700
Data Index: 6989183 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.4928. Min Act: -0.1700
Data Index: 4907093 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.4928. Min Act: -0.1700
Data Index: 1262877 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.4615. Min Act: -0.1700
Data Index: 5414819 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.4303. Min Act: -0.1700
Data Index: 6906320 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.3990. Min Act: -0.1700
Data Index: 3718696 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.3990. Min Act: -0.1700
Data Index: 2637650 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4615. Min Range: -8.4615
Max Act: 7.3678. Min Act: -0.1700
Data Index: 6600666 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19