Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.4731. Min Act: -0.1700
Data Index: 7674509 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.3793. Min Act: -0.1700
Data Index: 6651957 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.3168. Min Act: -0.1700
Data Index: 6651956 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.3168. Min Act: -0.1700
Data Index: 1388976 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.3168. Min Act: -0.1700
Data Index: 3671649 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2231. Min Act: -0.1700
Data Index: 1734430 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2543. Min Act: -0.1700
Data Index: 7611681 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2543. Min Act: -0.1700
Data Index: 6991464 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2543. Min Act: -0.1700
Data Index: 7510861 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2543. Min Act: -0.1700
Data Index: 97025 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2543. Min Act: -0.1700
Data Index: 70129 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2543. Min Act: -0.1700
Data Index: 1825017 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2231. Min Act: -0.1700
Data Index: 384630 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.2231. Min Act: -0.1700
Data Index: 8433580 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.1918. Min Act: -0.1700
Data Index: 3764779 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.1918. Min Act: -0.1700
Data Index: 6619398 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.1606. Min Act: -0.1700
Data Index: 3148823 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.1606. Min Act: -0.1700
Data Index: 7020637 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.1606. Min Act: -0.1700
Data Index: 1267502 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4731. Min Range: -4.4731
Max Act: 4.1606. Min Act: -0.1700
Data Index: 5251960 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19