Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.8183. Min Act: -0.1700
Data Index: 6368948 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.8496. Min Act: -0.1700
Data Index: 4403251 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5996. Min Act: -0.1700
Data Index: 7544120 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5371. Min Act: -0.1700
Data Index: 1542879 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5058. Min Act: -0.1700
Data Index: 133933 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5371. Min Act: -0.1700
Data Index: 8100808 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5058. Min Act: -0.1700
Data Index: 6915268 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5058. Min Act: -0.1700
Data Index: 3281781 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5058. Min Act: -0.1700
Data Index: 2647564 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.5058. Min Act: -0.1700
Data Index: 7676776 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.4746. Min Act: -0.1700
Data Index: 8340786 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.4746. Min Act: -0.1700
Data Index: 4284264 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.4746. Min Act: -0.1700
Data Index: 2805078 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.4121. Min Act: -0.1700
Data Index: 1698745 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.4121. Min Act: -0.1700
Data Index: 1464020 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.4121. Min Act: -0.1700
Data Index: 5599501 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.3808. Min Act: -0.1700
Data Index: 5082510 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.3808. Min Act: -0.1700
Data Index: 739691 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.3808. Min Act: -0.1700
Data Index: 3068974 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8496. Min Range: -5.8496
Max Act: 5.3808. Min Act: -0.1700
Data Index: 7225714 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19