Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4492 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0954. Min Range: -7.0954
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3025185 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0954. Min Range: -7.0954
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3791459 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0954. Min Range: -7.0954
Max Act: 7.0954. Min Act: -0.1700
Data Index: 511955 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.9391. Min Act: -0.1700
Data Index: 4692938 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.8766. Min Act: -0.1700
Data Index: 7577511 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.8766. Min Act: -0.1700
Data Index: 12896 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.8454. Min Act: -0.1700
Data Index: 880108 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.8766. Min Act: -0.1700
Data Index: 7080484 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.7829. Min Act: -0.1700
Data Index: 2743155 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.7829. Min Act: -0.1700
Data Index: 1998808 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.7829. Min Act: -0.1700
Data Index: 7648850 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.7516. Min Act: -0.1700
Data Index: 682446 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.7516. Min Act: -0.1700
Data Index: 5208031 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.7516. Min Act: -0.1700
Data Index: 1636640 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6891. Min Act: -0.1700
Data Index: 861045 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6891. Min Act: -0.1700
Data Index: 5962850 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6891. Min Act: -0.1700
Data Index: 1634187 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6579. Min Act: -0.1700
Data Index: 2755806 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6579. Min Act: -0.1700
Data Index: 6601430 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0954. Min Range: -7.0954
Max Act: 6.6579. Min Act: -0.1700
Data Index: 6480658 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19