Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.5116. Min Act: -0.1700
Data Index: 6746843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.5116. Min Act: -0.1700
Data Index: 2405434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4960. Min Act: -0.1700
Data Index: 8461305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4803. Min Act: -0.1700
Data Index: 6120816 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4646. Min Act: -0.1700
Data Index: 5663988 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 866294 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 6802706 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 2416770 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 6743348 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 7090790 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 6437069 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 8381403 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 2657587 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4333. Min Act: -0.1700
Data Index: 6378386 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 8247016 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4333. Min Act: -0.1700
Data Index: 7442039 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 1350303 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 1368948 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 3929381 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 1042467 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19