Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1164 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.1474. Min Act: -0.1700
Data Index: 5428296 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0849. Min Act: -0.1700
Data Index: 2017816 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0536. Min Act: -0.1700
Data Index: 4272093 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0223. Min Act: -0.1700
Data Index: 4607467 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0223. Min Act: -0.1700
Data Index: 1505776 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9911. Min Act: -0.1700
Data Index: 6749587 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0223. Min Act: -0.1700
Data Index: 2919737 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9911. Min Act: -0.1700
Data Index: 7456179 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3103490 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9598. Min Act: -0.1700
Data Index: 2969623 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9911. Min Act: -0.1700
Data Index: 56452 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9598. Min Act: -0.1700
Data Index: 8713951 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 1417463 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 65817 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 7384593 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 608515 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 5614725 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3559221 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 4827092 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.8973. Min Act: -0.1700
Data Index: 1000538 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19