Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.4488. Min Act: -0.1700
Data Index: 5344527 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.4488. Min Act: -0.1700
Data Index: 6576470 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.3238. Min Act: -0.1700
Data Index: 5651709 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.3238. Min Act: -0.1700
Data Index: 7894607 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.3238. Min Act: -0.1700
Data Index: 615132 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.3238. Min Act: -0.1700
Data Index: 7776843 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.2613. Min Act: -0.1700
Data Index: 434527 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.2613. Min Act: -0.1700
Data Index: 4746762 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.2613. Min Act: -0.1700
Data Index: 7266847 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.2613. Min Act: -0.1700
Data Index: 5062115 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1988. Min Act: -0.1700
Data Index: 2452606 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1988. Min Act: -0.1700
Data Index: 2889050 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 1432062 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1988. Min Act: -0.1700
Data Index: 8323212 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 4055863 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 6040776 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 4788615 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 4744019 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 5853159 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4488. Min Range: -7.4488
Max Act: 7.1363. Min Act: -0.1700
Data Index: 747888 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19