Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4777 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6162333 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.8271. Min Act: -0.1700
Data Index: 5147800 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7958. Min Act: -0.1700
Data Index: 4599994 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7958. Min Act: -0.1700
Data Index: 8311645 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7646. Min Act: -0.1700
Data Index: 7789912 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7333. Min Act: -0.1700
Data Index: 2298535 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.7020. Min Act: -0.1700
Data Index: 2644500 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6707. Min Act: -0.1700
Data Index: 8233308 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6707. Min Act: -0.1700
Data Index: 8368859 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6707. Min Act: -0.1700
Data Index: 1760736 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6707. Min Act: -0.1700
Data Index: 4599993 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 1521698 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 1300863 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 957219 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 428775 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6081. Min Act: -0.1700
Data Index: 2561029 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6394. Min Act: -0.1700
Data Index: 8059176 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.6081. Min Act: -0.1700
Data Index: 2555532 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.5768. Min Act: -0.1700
Data Index: 1300862 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9209. Min Range: -3.9209
Max Act: 3.5768. Min Act: -0.1700
Data Index: 5694215 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19