Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2411. Min Range: -7.2411
Max Act: 7.2411. Min Act: -0.1700
Data Index: 3765839 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2411. Min Range: -7.2411
Max Act: 7.1786. Min Act: -0.1700
Data Index: 3653771 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.8348. Min Act: -0.1700
Data Index: 1447593 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.7723. Min Act: -0.1700
Data Index: 2058485 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.6473. Min Act: -0.1700
Data Index: 6928978 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.4911. Min Act: -0.1700
Data Index: 3772982 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.4598. Min Act: -0.1700
Data Index: 6287510 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.4598. Min Act: -0.1700
Data Index: 3240862 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.4286. Min Act: -0.1700
Data Index: 5454096 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.3973. Min Act: -0.1700
Data Index: 2350907 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.3973. Min Act: -0.1700
Data Index: 3240861 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.3661. Min Act: -0.1700
Data Index: 1879794 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.3348. Min Act: -0.1700
Data Index: 946118 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.3036. Min Act: -0.1700
Data Index: 6531880 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.3036. Min Act: -0.1700
Data Index: 7153238 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.2723. Min Act: -0.1700
Data Index: 7472439 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.2411. Min Act: -0.1700
Data Index: 6531882 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.2411. Min Act: -0.1700
Data Index: 5560229 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.2411. Min Act: -0.1700
Data Index: 6682297 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2411. Min Range: -7.2411
Max Act: 6.2098. Min Act: -0.1700
Data Index: 657726 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19