Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6548. Min Range: -5.6548
Max Act: 5.6548. Min Act: -0.1700
Data Index: 8121330 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6548. Min Range: -5.6548
Max Act: 5.1548. Min Act: -0.1700
Data Index: 3705490 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6548. Min Range: -5.6548
Max Act: 5.0923. Min Act: -0.1700
Data Index: 281276 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6548. Min Range: -5.6548
Max Act: 5.1235. Min Act: -0.1700
Data Index: 2515021 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.9673. Min Act: -0.1700
Data Index: 2815047 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.8423. Min Act: -0.1700
Data Index: 6658536 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.8110. Min Act: -0.1700
Data Index: 1589328 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.8735. Min Act: -0.1700
Data Index: 588071 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.7798. Min Act: -0.1700
Data Index: 1569939 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.7798. Min Act: -0.1700
Data Index: 4392393 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.7485. Min Act: -0.1700
Data Index: 3575294 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.7173. Min Act: -0.1700
Data Index: 3701528 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6860. Min Act: -0.1700
Data Index: 5635252 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6548. Min Act: -0.1700
Data Index: 3577251 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6860. Min Act: -0.1700
Data Index: 3701374 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6860. Min Act: -0.1700
Data Index: 6401237 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6548. Min Act: -0.1700
Data Index: 696570 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6548. Min Act: -0.1700
Data Index: 8294558 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.6548. Min Act: -0.1700
Data Index: 2431525 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6548. Min Range: -5.6548
Max Act: 4.5923. Min Act: -0.1700
Data Index: 159591 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19