Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5202 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0884. Min Range: -6.0884
Max Act: 6.0884. Min Act: -0.1700
Data Index: 3356415 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.6509. Min Act: -0.1700
Data Index: 8270633 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.5884. Min Act: -0.1700
Data Index: 8061453 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.5572. Min Act: -0.1700
Data Index: 4965996 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4947. Min Act: -0.1700
Data Index: 4978636 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4947. Min Act: -0.1700
Data Index: 5052729 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4947. Min Act: -0.1700
Data Index: 6009082 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4947. Min Act: -0.1700
Data Index: 1962565 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4634. Min Act: -0.1700
Data Index: 8536851 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4739686 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4857027 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4322. Min Act: -0.1700
Data Index: 3473656 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4009. Min Act: -0.1700
Data Index: 6995603 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.4322. Min Act: -0.1700
Data Index: 2581149 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.3697. Min Act: -0.1700
Data Index: 1575442 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 8051424 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 3619856 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.3384. Min Act: -0.1700
Data Index: 676647 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.3072. Min Act: -0.1700
Data Index: 2467873 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0884. Min Range: -6.0884
Max Act: 5.3072. Min Act: -0.1700
Data Index: 6778224 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19