Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3728. Min Range: -8.3728
Max Act: 8.3728. Min Act: -0.1700
Data Index: 1435021 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.9040. Min Act: -0.1700
Data Index: 6072247 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.7790. Min Act: -0.1700
Data Index: 8540832 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.7790. Min Act: -0.1700
Data Index: 7663301 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.6853. Min Act: -0.1700
Data Index: 2465756 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.5290. Min Act: -0.1700
Data Index: 7930278 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.5290. Min Act: -0.1700
Data Index: 4926747 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.4353. Min Act: -0.1700
Data Index: 7015135 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.4040. Min Act: -0.1700
Data Index: 4756738 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.4040. Min Act: -0.1700
Data Index: 2137278 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.3415. Min Act: -0.1700
Data Index: 2506393 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.3415. Min Act: -0.1700
Data Index: 1502031 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.3415. Min Act: -0.1700
Data Index: 8025440 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.3415. Min Act: -0.1700
Data Index: 7369792 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.3103. Min Act: -0.1700
Data Index: 2447150 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.2478. Min Act: -0.1700
Data Index: 6760511 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.2790. Min Act: -0.1700
Data Index: 7943706 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.2478. Min Act: -0.1700
Data Index: 1452932 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.2478. Min Act: -0.1700
Data Index: 3123115 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3728. Min Range: -8.3728
Max Act: 7.2165. Min Act: -0.1700
Data Index: 8472605 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19