Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0538. Min Range: -8.0538
Max Act: 8.0538. Min Act: -0.1700
Data Index: 4587876 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.8975. Min Act: -0.1700
Data Index: 5220466 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.8350. Min Act: -0.1700
Data Index: 8152332 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.5538. Min Act: -0.1700
Data Index: 7697167 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.4913. Min Act: -0.1700
Data Index: 7333406 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.4913. Min Act: -0.1700
Data Index: 1195297 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.4288. Min Act: -0.1700
Data Index: 4779483 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.4288. Min Act: -0.1700
Data Index: 2475270 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.3350. Min Act: -0.1700
Data Index: 6448893 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.3038. Min Act: -0.1700
Data Index: 376860 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.2725. Min Act: -0.1700
Data Index: 2614933 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.2413. Min Act: -0.1700
Data Index: 7958873 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.2100. Min Act: -0.1700
Data Index: 4025155 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.2413. Min Act: -0.1700
Data Index: 4158976 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.2413. Min Act: -0.1700
Data Index: 4220919 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.1788. Min Act: -0.1700
Data Index: 4064562 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.1788. Min Act: -0.1700
Data Index: 6785729 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.1788. Min Act: -0.1700
Data Index: 5236353 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.1475. Min Act: -0.1700
Data Index: 169444 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0538. Min Range: -8.0538
Max Act: 7.1788. Min Act: -0.1700
Data Index: 4884116 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19