Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.2704. Min Act: -0.1700
Data Index: 2174894 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.1766. Min Act: -0.1700
Data Index: 5104410 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.1766. Min Act: -0.1700
Data Index: 8118127 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.1454. Min Act: -0.1700
Data Index: 1439846 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.9579. Min Act: -0.1700
Data Index: 3001911 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1439845 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8954. Min Act: -0.1700
Data Index: 1514632 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8641. Min Act: -0.1700
Data Index: 810834 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8641. Min Act: -0.1700
Data Index: 6759777 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8641. Min Act: -0.1700
Data Index: 2540187 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8641. Min Act: -0.1700
Data Index: 41303 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 7838013 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 1875176 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 8631577 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 8257220 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1718128 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1474511 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 6899287 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1002131 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4390310 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19