Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.7645. Min Act: -0.1700
Data Index: 6583502 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.6082. Min Act: -0.1700
Data Index: 8551114 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.2957. Min Act: -0.1700
Data Index: 6405212 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.2332. Min Act: -0.1700
Data Index: 7441883 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.2020. Min Act: -0.1700
Data Index: 7614709 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.1707. Min Act: -0.1700
Data Index: 2499368 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.1082. Min Act: -0.1700
Data Index: 176531 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.1082. Min Act: -0.1700
Data Index: 6377700 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.1082. Min Act: -0.1700
Data Index: 242199 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.0457. Min Act: -0.1700
Data Index: 2311879 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.0457. Min Act: -0.1700
Data Index: 5207541 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.0145. Min Act: -0.1700
Data Index: 5916285 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.0145. Min Act: -0.1700
Data Index: 8612854 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7645. Min Range: -7.7645
Max Act: 7.0457. Min Act: -0.1700
Data Index: 3377821 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7645. Min Range: -7.7645
Max Act: 6.9520. Min Act: -0.1700
Data Index: 3033920 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7645. Min Range: -7.7645
Max Act: 6.9207. Min Act: -0.1700
Data Index: 1807340 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7645. Min Range: -7.7645
Max Act: 6.9520. Min Act: -0.1700
Data Index: 7067810 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7645. Min Range: -7.7645
Max Act: 6.8895. Min Act: -0.1700
Data Index: 3356265 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7645. Min Range: -7.7645
Max Act: 6.9520. Min Act: -0.1700
Data Index: 876423 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7645. Min Range: -7.7645
Max Act: 6.8582. Min Act: -0.1700
Data Index: 3953040 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19