Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.4356. Min Act: -0.1700
Data Index: 6127528 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.4356. Min Act: -0.1700
Data Index: 342129 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.4669. Min Act: -0.1700
Data Index: 4099223 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.4199. Min Act: -0.1700
Data Index: 5108363 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.4199. Min Act: -0.1700
Data Index: 2877018 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.4042. Min Act: -0.1700
Data Index: 5108364 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3572. Min Act: -0.1700
Data Index: 2877017 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3729. Min Act: -0.1700
Data Index: 5615079 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3572. Min Act: -0.1700
Data Index: 43288 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3415. Min Act: -0.1700
Data Index: 4099222 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3258. Min Act: -0.1700
Data Index: 7650874 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3101. Min Act: -0.1700
Data Index: 7403318 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2787. Min Act: -0.1700
Data Index: 6140799 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.3101. Min Act: -0.1700
Data Index: 2104226 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2159. Min Act: -0.1700
Data Index: 6368333 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2787. Min Act: -0.1700
Data Index: 4981299 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2316. Min Act: -0.1700
Data Index: 4832145 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2630. Min Act: -0.1700
Data Index: 4881585 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2473. Min Act: -0.1700
Data Index: 4832129 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4669. Min Range: -3.4669
Max Act: 3.2473. Min Act: -0.1700
Data Index: 2104222 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19