Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.8300. Min Act: -0.1700
Data Index: 5630792 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.8300. Min Act: -0.1700
Data Index: 2063363 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.7675. Min Act: -0.1700
Data Index: 5241932 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.7050. Min Act: -0.1700
Data Index: 7053899 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.6425. Min Act: -0.1700
Data Index: 5393560 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.5800. Min Act: -0.1700
Data Index: 8678486 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.5800. Min Act: -0.1700
Data Index: 5709838 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.5175. Min Act: -0.1700
Data Index: 761746 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.5175. Min Act: -0.1700
Data Index: 716096 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.5175. Min Act: -0.1700
Data Index: 8523998 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.5175. Min Act: -0.1700
Data Index: 2798492 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.4550. Min Act: -0.1700
Data Index: 4290304 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.3925. Min Act: -0.1700
Data Index: 4933903 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.3300. Min Act: -0.1700
Data Index: 1878607 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.3300. Min Act: -0.1700
Data Index: 1277449 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.3300. Min Act: -0.1700
Data Index: 2790785 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.3300. Min Act: -0.1700
Data Index: 727342 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.2675. Min Act: -0.1700
Data Index: 1282252 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.2675. Min Act: -0.1700
Data Index: 4912028 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8300. Min Range: -9.8300
Max Act: 9.2675. Min Act: -0.1700
Data Index: 3960412 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19