Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2078 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2396. Min Range: -7.2396
Max Act: 7.2396. Min Act: -0.1700
Data Index: 2495956 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2396. Min Range: -7.2396
Max Act: 7.0209. Min Act: -0.1700
Data Index: 7979612 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.9896. Min Act: -0.1700
Data Index: 4693142 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.8959. Min Act: -0.1700
Data Index: 8548593 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.9271. Min Act: -0.1700
Data Index: 4688432 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.8334. Min Act: -0.1700
Data Index: 7848509 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.8334. Min Act: -0.1700
Data Index: 6005986 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.8334. Min Act: -0.1700
Data Index: 8095790 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.8021. Min Act: -0.1700
Data Index: 5982753 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.8021. Min Act: -0.1700
Data Index: 4398655 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7709. Min Act: -0.1700
Data Index: 3003670 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 6746070 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7709. Min Act: -0.1700
Data Index: 8415449 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7709. Min Act: -0.1700
Data Index: 8455173 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 7147318 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 585122 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 409659 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 8415443 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 15533 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2396. Min Range: -7.2396
Max Act: 6.6771. Min Act: -0.1700
Data Index: 2451134 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19