Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.5735. Min Act: -0.1700
Data Index: 6633512 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.5735. Min Act: -0.1700
Data Index: 4143593 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.5578. Min Act: -0.1700
Data Index: 6532947 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.5422. Min Act: -0.1700
Data Index: 5196857 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.5109. Min Act: -0.1700
Data Index: 8541456 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4952. Min Act: -0.1700
Data Index: 7460533 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.5109. Min Act: -0.1700
Data Index: 8685555 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4795. Min Act: -0.1700
Data Index: 2251972 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4795. Min Act: -0.1700
Data Index: 3460676 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4639. Min Act: -0.1700
Data Index: 8402465 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4482. Min Act: -0.1700
Data Index: 2935878 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4325. Min Act: -0.1700
Data Index: 2513666 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4168. Min Act: -0.1700
Data Index: 4054260 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4325. Min Act: -0.1700
Data Index: 4152853 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4168. Min Act: -0.1700
Data Index: 3266730 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4168. Min Act: -0.1700
Data Index: 165681 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4168. Min Act: -0.1700
Data Index: 5077046 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.4168. Min Act: -0.1700
Data Index: 3269129 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.3855. Min Act: -0.1700
Data Index: 4680498 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5735. Min Range: -3.5735
Max Act: 3.3698. Min Act: -0.1700
Data Index: 6868408 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19