Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.4816. Min Act: -0.1700
Data Index: 2464247 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.4504. Min Act: -0.1700
Data Index: 2978704 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.3566. Min Act: -0.1700
Data Index: 978454 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.3254. Min Act: -0.1700
Data Index: 8109697 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2941. Min Act: -0.1700
Data Index: 6375939 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2941. Min Act: -0.1700
Data Index: 1554242 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.3254. Min Act: -0.1700
Data Index: 171897 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2941. Min Act: -0.1700
Data Index: 4060988 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2629. Min Act: -0.1700
Data Index: 5299472 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2629. Min Act: -0.1700
Data Index: 4462733 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2003. Min Act: -0.1700
Data Index: 5090384 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2316. Min Act: -0.1700
Data Index: 3387135 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2316. Min Act: -0.1700
Data Index: 6258587 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.2316. Min Act: -0.1700
Data Index: 4484866 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.1691. Min Act: -0.1700
Data Index: 2971232 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.1691. Min Act: -0.1700
Data Index: 2984445 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.1378. Min Act: -0.1700
Data Index: 4697553 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.1691. Min Act: -0.1700
Data Index: 5597959 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.1691. Min Act: -0.1700
Data Index: 2129518 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4816. Min Range: -4.4816
Max Act: 4.1691. Min Act: -0.1700
Data Index: 7468506 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19