Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.7550. Min Act: -0.1700
Data Index: 3000818 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.7238. Min Act: -0.1700
Data Index: 5268 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6677867 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.5050. Min Act: -0.1700
Data Index: 7298631 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.5050. Min Act: -0.1700
Data Index: 7570611 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.4738. Min Act: -0.1700
Data Index: 7538384 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.4738. Min Act: -0.1700
Data Index: 178008 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.4425. Min Act: -0.1700
Data Index: 3082382 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.4425. Min Act: -0.1700
Data Index: 1399599 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.4425. Min Act: -0.1700
Data Index: 5562511 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3800. Min Act: -0.1700
Data Index: 7964406 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3800. Min Act: -0.1700
Data Index: 5403213 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3800. Min Act: -0.1700
Data Index: 4370527 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3800. Min Act: -0.1700
Data Index: 5418836 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3488. Min Act: -0.1700
Data Index: 4691713 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3175. Min Act: -0.1700
Data Index: 8424481 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.3175. Min Act: -0.1700
Data Index: 841483 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.2863. Min Act: -0.1700
Data Index: 1705889 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.2238. Min Act: -0.1700
Data Index: 1061685 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7550. Min Range: -6.7550
Max Act: 6.2238. Min Act: -0.1700
Data Index: 2228023 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19