Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.4624. Min Act: -0.1700
Data Index: 3867388 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.3061. Min Act: -0.1700
Data Index: 5010934 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.2749. Min Act: -0.1700
Data Index: 7343608 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.2436. Min Act: -0.1700
Data Index: 5912076 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.2124. Min Act: -0.1700
Data Index: 5676640 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.1499. Min Act: -0.1700
Data Index: 3028375 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.1186. Min Act: -0.1700
Data Index: 7103721 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.1186. Min Act: -0.1700
Data Index: 5033079 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.0874. Min Act: -0.1700
Data Index: 3758991 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.0874. Min Act: -0.1700
Data Index: 1976596 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.0249. Min Act: -0.1700
Data Index: 4601538 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.0561. Min Act: -0.1700
Data Index: 2858525 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.9936. Min Act: -0.1700
Data Index: 7962861 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.9936. Min Act: -0.1700
Data Index: 7112568 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4624. Min Range: -6.4624
Max Act: 6.0249. Min Act: -0.1700
Data Index: 7314215 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.9311. Min Act: -0.1700
Data Index: 7756056 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.9311. Min Act: -0.1700
Data Index: 5338180 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.9624. Min Act: -0.1700
Data Index: 7311836 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.8999. Min Act: -0.1700
Data Index: 6493656 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4624. Min Range: -6.4624
Max Act: 5.9936. Min Act: -0.1700
Data Index: 6471237 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19