Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2328 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0888. Min Range: -7.0888
Max Act: 7.0888. Min Act: -0.1700
Data Index: 5595175 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0888. Min Range: -7.0888
Max Act: 7.0575. Min Act: -0.1700
Data Index: 2169038 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9950. Min Act: -0.1700
Data Index: 6807705 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9950. Min Act: -0.1700
Data Index: 6688264 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9950. Min Act: -0.1700
Data Index: 6852255 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9950. Min Act: -0.1700
Data Index: 2894696 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9638. Min Act: -0.1700
Data Index: 6677601 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9638. Min Act: -0.1700
Data Index: 8545514 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9325. Min Act: -0.1700
Data Index: 3266716 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.9325. Min Act: -0.1700
Data Index: 4437602 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.8700. Min Act: -0.1700
Data Index: 5813754 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.8388. Min Act: -0.1700
Data Index: 2509454 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.8075. Min Act: -0.1700
Data Index: 3731034 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.8388. Min Act: -0.1700
Data Index: 6792114 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.8075. Min Act: -0.1700
Data Index: 302548 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.7763. Min Act: -0.1700
Data Index: 1336267 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.7763. Min Act: -0.1700
Data Index: 3012805 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.7763. Min Act: -0.1700
Data Index: 5124106 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.7763. Min Act: -0.1700
Data Index: 5497427 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0888. Min Range: -7.0888
Max Act: 6.7763. Min Act: -0.1700
Data Index: 3522118 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19