Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.6569. Min Act: -0.1700
Data Index: 2558249 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.5944. Min Act: -0.1700
Data Index: 8580288 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.5944. Min Act: -0.1700
Data Index: 7327879 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.5944. Min Act: -0.1700
Data Index: 7198401 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.4694. Min Act: -0.1700
Data Index: 2741628 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.4694. Min Act: -0.1700
Data Index: 2987921 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.4694. Min Act: -0.1700
Data Index: 7310363 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.4069. Min Act: -0.1700
Data Index: 6637146 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.4069. Min Act: -0.1700
Data Index: 2258576 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.3444. Min Act: -0.1700
Data Index: 1036870 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.3444. Min Act: -0.1700
Data Index: 6559990 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.3444. Min Act: -0.1700
Data Index: 8682715 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.2819. Min Act: -0.1700
Data Index: 4451256 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.1569. Min Act: -0.1700
Data Index: 2118552 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.2194. Min Act: -0.1700
Data Index: 7765483 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.2194. Min Act: -0.1700
Data Index: 6284586 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.2194. Min Act: -0.1700
Data Index: 8035782 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.1569. Min Act: -0.1700
Data Index: 3591938 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.1569. Min Act: -0.1700
Data Index: 17234 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6569. Min Range: -8.6569
Max Act: 8.1569. Min Act: -0.1700
Data Index: 1916247 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19