Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4686 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.8513. Min Act: -0.1700
Data Index: 5129305 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.8200. Min Act: -0.1700
Data Index: 7943964 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.8200. Min Act: -0.1700
Data Index: 2869928 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.7888. Min Act: -0.1700
Data Index: 7322586 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.6950. Min Act: -0.1700
Data Index: 6402801 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.6638. Min Act: -0.1700
Data Index: 7442189 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.6638. Min Act: -0.1700
Data Index: 4062051 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5700. Min Act: -0.1700
Data Index: 4184700 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.6013. Min Act: -0.1700
Data Index: 3142014 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5700. Min Act: -0.1700
Data Index: 7608886 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5388. Min Act: -0.1700
Data Index: 2680074 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5388. Min Act: -0.1700
Data Index: 6966919 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5388. Min Act: -0.1700
Data Index: 6423286 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5388. Min Act: -0.1700
Data Index: 7601240 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5388. Min Act: -0.1700
Data Index: 494904 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5388. Min Act: -0.1700
Data Index: 7250511 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.4763. Min Act: -0.1700
Data Index: 128060 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5075. Min Act: -0.1700
Data Index: 4253845 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.4763. Min Act: -0.1700
Data Index: 4812105 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8513. Min Range: -5.8513
Max Act: 5.5075. Min Act: -0.1700
Data Index: 7196113 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19