Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3457. Min Range: -5.3457
Max Act: 5.3457. Min Act: -0.1700
Data Index: 7968727 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3457. Min Range: -5.3457
Max Act: 5.3457. Min Act: -0.1700
Data Index: 5469670 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3457. Min Range: -5.3457
Max Act: 5.2207. Min Act: -0.1700
Data Index: 1196488 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3457. Min Range: -5.3457
Max Act: 5.0957. Min Act: -0.1700
Data Index: 608517 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3457. Min Range: -5.3457
Max Act: 5.0019. Min Act: -0.1700
Data Index: 3419482 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3457. Min Range: -5.3457
Max Act: 5.0019. Min Act: -0.1700
Data Index: 3511732 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.9707. Min Act: -0.1700
Data Index: 8076312 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.9394. Min Act: -0.1700
Data Index: 6288413 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.9082. Min Act: -0.1700
Data Index: 7186106 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.8769. Min Act: -0.1700
Data Index: 1806596 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.8457. Min Act: -0.1700
Data Index: 8050108 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.8457. Min Act: -0.1700
Data Index: 934496 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.8144. Min Act: -0.1700
Data Index: 5149479 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.8144. Min Act: -0.1700
Data Index: 4554992 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.7519. Min Act: -0.1700
Data Index: 7376727 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.7519. Min Act: -0.1700
Data Index: 3712401 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.7832. Min Act: -0.1700
Data Index: 7786249 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.7519. Min Act: -0.1700
Data Index: 2093459 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.7519. Min Act: -0.1700
Data Index: 4818246 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3457. Min Range: -5.3457
Max Act: 4.7832. Min Act: -0.1700
Data Index: 879378 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19