Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.9253. Min Act: -0.1700
Data Index: 852605 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.9566. Min Act: -0.1700
Data Index: 861234 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8316. Min Act: -0.1700
Data Index: 1174698 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8628. Min Act: -0.1700
Data Index: 6872983 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8628. Min Act: -0.1700
Data Index: 3012253 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8628. Min Act: -0.1700
Data Index: 6786116 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8003. Min Act: -0.1700
Data Index: 3403667 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8003. Min Act: -0.1700
Data Index: 8574428 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8003. Min Act: -0.1700
Data Index: 8573672 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8316. Min Act: -0.1700
Data Index: 4006683 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.8003. Min Act: -0.1700
Data Index: 7016210 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7691. Min Act: -0.1700
Data Index: 1972657 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7378. Min Act: -0.1700
Data Index: 8698494 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 7523275 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 6487867 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.7066. Min Act: -0.1700
Data Index: 4858930 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.6753. Min Act: -0.1700
Data Index: 6981161 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.6753. Min Act: -0.1700
Data Index: 1064401 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.6753. Min Act: -0.1700
Data Index: 961938 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9566. Min Range: -4.9566
Max Act: 4.6753. Min Act: -0.1700
Data Index: 5498539 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19