Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5692 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2639. Min Range: -9.2639
Max Act: 9.2639. Min Act: -0.1700
Data Index: 6965235 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2639. Min Range: -9.2639
Max Act: 9.1389. Min Act: -0.1700
Data Index: 865032 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2639. Min Range: -9.2639
Max Act: 9.0764. Min Act: -0.1700
Data Index: 7643340 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.9514. Min Act: -0.1700
Data Index: 6875367 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2639. Min Range: -9.2639
Max Act: 9.0139. Min Act: -0.1700
Data Index: 5179502 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.8889. Min Act: -0.1700
Data Index: 1169876 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.8889. Min Act: -0.1700
Data Index: 7691686 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.8264. Min Act: -0.1700
Data Index: 5342184 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.7639. Min Act: -0.1700
Data Index: 1572518 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.6389. Min Act: -0.1700
Data Index: 358811 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.5139. Min Act: -0.1700
Data Index: 6117387 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.5139. Min Act: -0.1700
Data Index: 4829649 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.4514. Min Act: -0.1700
Data Index: 3479409 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.3264. Min Act: -0.1700
Data Index: 6769753 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.3889. Min Act: -0.1700
Data Index: 4522950 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.3889. Min Act: -0.1700
Data Index: 356444 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.3264. Min Act: -0.1700
Data Index: 6317416 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.2639. Min Act: -0.1700
Data Index: 7237121 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.3264. Min Act: -0.1700
Data Index: 6072632 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2639. Min Range: -9.2639
Max Act: 8.2639. Min Act: -0.1700
Data Index: 7113849 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19