Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6348 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8825. Min Range: -9.8825
Max Act: 9.8825. Min Act: -0.1700
Data Index: 8553204 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8825. Min Range: -9.8825
Max Act: 9.3825. Min Act: -0.1700
Data Index: 5906876 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8825. Min Range: -9.8825
Max Act: 9.1950. Min Act: -0.1700
Data Index: 2543095 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.9450. Min Act: -0.1700
Data Index: 8675472 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.8825. Min Act: -0.1700
Data Index: 2380548 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.8825. Min Act: -0.1700
Data Index: 7653325 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.8825. Min Act: -0.1700
Data Index: 7182426 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.8200. Min Act: -0.1700
Data Index: 3822193 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.8200. Min Act: -0.1700
Data Index: 5420381 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.7575. Min Act: -0.1700
Data Index: 6126406 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.7575. Min Act: -0.1700
Data Index: 2309030 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.7575. Min Act: -0.1700
Data Index: 1229935 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.6950. Min Act: -0.1700
Data Index: 5869929 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.6950. Min Act: -0.1700
Data Index: 7855994 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.6950. Min Act: -0.1700
Data Index: 3553730 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.6950. Min Act: -0.1700
Data Index: 3050972 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.6325. Min Act: -0.1700
Data Index: 8450501 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.6325. Min Act: -0.1700
Data Index: 7277970 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.5700. Min Act: -0.1700
Data Index: 836987 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8825. Min Range: -9.8825
Max Act: 8.5700. Min Act: -0.1700
Data Index: 4879609 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19