Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5940 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0953. Min Range: -8.0953
Max Act: 8.0953. Min Act: -0.1700
Data Index: 3346624 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.9390. Min Act: -0.1700
Data Index: 2673160 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.5015. Min Act: -0.1700
Data Index: 6532504 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.3765. Min Act: -0.1700
Data Index: 4028270 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.4078. Min Act: -0.1700
Data Index: 4634432 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.3765. Min Act: -0.1700
Data Index: 8399343 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.3140. Min Act: -0.1700
Data Index: 2647707 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.3140. Min Act: -0.1700
Data Index: 5887573 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.3140. Min Act: -0.1700
Data Index: 4567061 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2828. Min Act: -0.1700
Data Index: 8123419 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2515. Min Act: -0.1700
Data Index: 1380640 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2515. Min Act: -0.1700
Data Index: 553530 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2515. Min Act: -0.1700
Data Index: 62704 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2203. Min Act: -0.1700
Data Index: 4463883 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2203. Min Act: -0.1700
Data Index: 639078 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.1890. Min Act: -0.1700
Data Index: 3573950 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.2203. Min Act: -0.1700
Data Index: 5302432 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.1890. Min Act: -0.1700
Data Index: 230617 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.1890. Min Act: -0.1700
Data Index: 4168931 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0953. Min Range: -8.0953
Max Act: 7.1578. Min Act: -0.1700
Data Index: 2277777 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19