Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.4362. Min Act: -0.1700
Data Index: 7556929 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.2799. Min Act: -0.1700
Data Index: 7726163 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.2487. Min Act: -0.1700
Data Index: 8772136 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.2799. Min Act: -0.1700
Data Index: 3364675 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.2174. Min Act: -0.1700
Data Index: 357393 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.2174. Min Act: -0.1700
Data Index: 1961031 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5422946 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.1549. Min Act: -0.1700
Data Index: 4361638 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.1862. Min Act: -0.1700
Data Index: 1892462 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.1237. Min Act: -0.1700
Data Index: 8761760 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.1237. Min Act: -0.1700
Data Index: 2267383 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.1237. Min Act: -0.1700
Data Index: 4600663 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.0924. Min Act: -0.1700
Data Index: 5615285 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.0612. Min Act: -0.1700
Data Index: 7919469 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.0612. Min Act: -0.1700
Data Index: 357395 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.0612. Min Act: -0.1700
Data Index: 7162549 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.0299. Min Act: -0.1700
Data Index: 5396250 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4362. Min Range: -5.4362
Max Act: 5.0299. Min Act: -0.1700
Data Index: 3087791 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4362. Min Range: -5.4362
Max Act: 4.9987. Min Act: -0.1700
Data Index: 7957522 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4362. Min Range: -5.4362
Max Act: 4.9987. Min Act: -0.1700
Data Index: 1634774 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19