Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.2138. Min Act: -0.1700
Data Index: 1204902 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.2138. Min Act: -0.1700
Data Index: 3565104 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.1826. Min Act: -0.1700
Data Index: 4047968 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.1201. Min Act: -0.1700
Data Index: 5147330 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.0576. Min Act: -0.1700
Data Index: 8590438 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.0888. Min Act: -0.1700
Data Index: 350328 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2138. Min Range: -6.2138
Max Act: 6.0263. Min Act: -0.1700
Data Index: 363155 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9951. Min Act: -0.1700
Data Index: 2468545 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9951. Min Act: -0.1700
Data Index: 7468990 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9638. Min Act: -0.1700
Data Index: 3304507 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9326. Min Act: -0.1700
Data Index: 4659705 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9326. Min Act: -0.1700
Data Index: 8285951 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9326. Min Act: -0.1700
Data Index: 3928614 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.8701. Min Act: -0.1700
Data Index: 7995020 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9013. Min Act: -0.1700
Data Index: 3219155 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9013. Min Act: -0.1700
Data Index: 8205626 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.8701. Min Act: -0.1700
Data Index: 4282031 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.9013. Min Act: -0.1700
Data Index: 8254220 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.8388. Min Act: -0.1700
Data Index: 1707197 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2138. Min Range: -6.2138
Max Act: 5.8076. Min Act: -0.1700
Data Index: 1707196 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19