Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.6499. Min Act: -0.1700
Data Index: 647084 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.6186. Min Act: -0.1700
Data Index: 6789930 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4936. Min Act: -0.1700
Data Index: 7370437 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4936. Min Act: -0.1700
Data Index: 3674622 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4624. Min Act: -0.1700
Data Index: 3398095 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4936. Min Act: -0.1700
Data Index: 5411829 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4624. Min Act: -0.1700
Data Index: 2084986 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4624. Min Act: -0.1700
Data Index: 2630467 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.4311. Min Act: -0.1700
Data Index: 15660 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3999. Min Act: -0.1700
Data Index: 167463 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3999. Min Act: -0.1700
Data Index: 4517221 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3999. Min Act: -0.1700
Data Index: 6086197 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3999. Min Act: -0.1700
Data Index: 1494589 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3686. Min Act: -0.1700
Data Index: 932361 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3686. Min Act: -0.1700
Data Index: 781610 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3686. Min Act: -0.1700
Data Index: 8679007 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3374. Min Act: -0.1700
Data Index: 6093153 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3374. Min Act: -0.1700
Data Index: 3734793 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3686. Min Act: -0.1700
Data Index: 7138739 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6499. Min Range: -4.6499
Max Act: 4.3374. Min Act: -0.1700
Data Index: 6019843 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19