Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.3695. Min Act: -0.1700
Data Index: 5724316 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.3695. Min Act: -0.1700
Data Index: 6116294 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.3382. Min Act: -0.1700
Data Index: 3682996 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.2757. Min Act: -0.1700
Data Index: 7966434 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.2132. Min Act: -0.1700
Data Index: 7862175 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1820. Min Act: -0.1700
Data Index: 1220415 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1820. Min Act: -0.1700
Data Index: 7156202 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1507. Min Act: -0.1700
Data Index: 20618 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7689833 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1507. Min Act: -0.1700
Data Index: 5679396 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1195. Min Act: -0.1700
Data Index: 169097 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.1195. Min Act: -0.1700
Data Index: 7722929 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0882. Min Act: -0.1700
Data Index: 1946053 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0882. Min Act: -0.1700
Data Index: 6439753 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0882. Min Act: -0.1700
Data Index: 3086791 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0882. Min Act: -0.1700
Data Index: 8642671 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0257. Min Act: -0.1700
Data Index: 424261 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0882. Min Act: -0.1700
Data Index: 1220414 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0570. Min Act: -0.1700
Data Index: 4212610 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3695. Min Range: -5.3695
Max Act: 5.0570. Min Act: -0.1700
Data Index: 551833 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19