Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5718 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.9907. Min Act: -0.1700
Data Index: 2053344 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.9594. Min Act: -0.1700
Data Index: 4831632 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.9282. Min Act: -0.1700
Data Index: 3904190 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.8969. Min Act: -0.1700
Data Index: 3904193 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.8969. Min Act: -0.1700
Data Index: 1000703 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.8344. Min Act: -0.1700
Data Index: 5968132 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.8344. Min Act: -0.1700
Data Index: 4226832 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.8032. Min Act: -0.1700
Data Index: 4301468 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.8032. Min Act: -0.1700
Data Index: 2138724 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 2142436 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 7437975 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7407. Min Act: -0.1700
Data Index: 969718 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 2258936 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 1804617 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 780259 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7407. Min Act: -0.1700
Data Index: 8210023 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 403235 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7719. Min Act: -0.1700
Data Index: 5653482 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7407. Min Act: -0.1700
Data Index: 3461085 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9907. Min Range: -4.9907
Max Act: 4.7407. Min Act: -0.1700
Data Index: 3478294 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19