Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.8727. Min Act: -0.1700
Data Index: 5668188 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.5598. Min Act: -0.1700
Data Index: 714746 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.5128. Min Act: -0.1700
Data Index: 210606 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4972. Min Act: -0.1700
Data Index: 520841 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4658. Min Act: -0.1700
Data Index: 8289110 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4972. Min Act: -0.1700
Data Index: 2434499 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4815. Min Act: -0.1700
Data Index: 4178226 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4345. Min Act: -0.1700
Data Index: 2648334 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4345. Min Act: -0.1700
Data Index: 8099826 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4031. Min Act: -0.1700
Data Index: 1305200 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.4188. Min Act: -0.1700
Data Index: 674026 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3718. Min Act: -0.1700
Data Index: 1094510 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3875. Min Act: -0.1700
Data Index: 7827565 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3875. Min Act: -0.1700
Data Index: 4444060 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3404. Min Act: -0.1700
Data Index: 1964448 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3718. Min Act: -0.1700
Data Index: 4471838 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3247. Min Act: -0.1700
Data Index: 3578831 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.2933. Min Act: -0.1699
Data Index: 3338885 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.3090. Min Act: -0.1700
Data Index: 4916828 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8727. Min Range: -3.8727
Max Act: 3.2776. Min Act: -0.1632
Data Index: 6850071 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19