Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5960 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.8950. Min Act: -0.1700
Data Index: 2844293 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.8012. Min Act: -0.1700
Data Index: 5382661 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.6450. Min Act: -0.1700
Data Index: 155841 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.6137. Min Act: -0.1700
Data Index: 4737085 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1749258 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.5512. Min Act: -0.1700
Data Index: 328794 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.5512. Min Act: -0.1700
Data Index: 2784326 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.5512. Min Act: -0.1700
Data Index: 7553341 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.5512. Min Act: -0.1700
Data Index: 2856648 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.5200. Min Act: -0.1700
Data Index: 8270681 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.5200. Min Act: -0.1700
Data Index: 2837563 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4887. Min Act: -0.1700
Data Index: 7018138 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4887. Min Act: -0.1700
Data Index: 71549 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4575. Min Act: -0.1700
Data Index: 2784341 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4887. Min Act: -0.1700
Data Index: 2083890 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4887. Min Act: -0.1700
Data Index: 6852840 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4575. Min Act: -0.1700
Data Index: 4495514 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4575. Min Act: -0.1700
Data Index: 3506194 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4575. Min Act: -0.1700
Data Index: 4716468 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8950. Min Range: -6.8950
Max Act: 6.4575. Min Act: -0.1700
Data Index: 168338 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19