Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8362. Min Act: -0.1700
Data Index: 7391029 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8049. Min Act: -0.1700
Data Index: 3243391 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8049. Min Act: -0.1700
Data Index: 782398 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7580. Min Act: -0.1700
Data Index: 3189708 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7423. Min Act: -0.1700
Data Index: 8390187 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7423. Min Act: -0.1700
Data Index: 7345930 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7267. Min Act: -0.1700
Data Index: 7131739 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 3255624 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 3837720 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6954. Min Act: -0.1700
Data Index: 2297398 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 2184329 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6798. Min Act: -0.1700
Data Index: 3184878 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6798. Min Act: -0.1700
Data Index: 8367738 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6954. Min Act: -0.1700
Data Index: 6704167 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6798. Min Act: -0.1700
Data Index: 876995 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6328. Min Act: -0.1700
Data Index: 3481003 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6328. Min Act: -0.1700
Data Index: 8128274 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 1234566 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 3587694 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 1511728 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19