Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1788 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1735. Min Range: -4.1735
Max Act: 4.1735. Min Act: -0.1700
Data Index: 6568699 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1735. Min Range: -4.1735
Max Act: 4.0485. Min Act: -0.1700
Data Index: 4164095 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1735. Min Range: -4.1735
Max Act: 4.0172. Min Act: -0.1700
Data Index: 3682560 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.9078. Min Act: -0.1700
Data Index: 8622715 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.9234. Min Act: -0.1700
Data Index: 5675946 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.8609. Min Act: -0.1700
Data Index: 2310000 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.8140. Min Act: -0.1700
Data Index: 1174148 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7671. Min Act: -0.1700
Data Index: 9673 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.8140. Min Act: -0.1700
Data Index: 8142332 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.8140. Min Act: -0.1700
Data Index: 6021343 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7827. Min Act: -0.1700
Data Index: 4224572 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7514. Min Act: -0.1700
Data Index: 6979394 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7671. Min Act: -0.1700
Data Index: 6196971 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7983. Min Act: -0.1700
Data Index: 742511 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7514. Min Act: -0.1700
Data Index: 3918132 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7514. Min Act: -0.1700
Data Index: 2518541 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7202. Min Act: -0.1700
Data Index: 7256911 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7358. Min Act: -0.1700
Data Index: 632206 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7514. Min Act: -0.1700
Data Index: 5396232 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1735. Min Range: -4.1735
Max Act: 3.7358. Min Act: -0.1700
Data Index: 1070743 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19