Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.5124. Min Act: -0.1700
Data Index: 3136760 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.4499. Min Act: -0.1700
Data Index: 3136757 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.4186. Min Act: -0.1700
Data Index: 3136762 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.4186. Min Act: -0.1700
Data Index: 3136756 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3874. Min Act: -0.1700
Data Index: 3136777 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3874. Min Act: -0.1700
Data Index: 3136768 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3874. Min Act: -0.1700
Data Index: 3136750 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.4186. Min Act: -0.1700
Data Index: 3136771 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3561. Min Act: -0.1700
Data Index: 3136748 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3249. Min Act: -0.1700
Data Index: 7165288 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3249. Min Act: -0.1700
Data Index: 3136742 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2936. Min Act: -0.1700
Data Index: 6773416 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2936. Min Act: -0.1700
Data Index: 3136747 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2936. Min Act: -0.1700
Data Index: 3136776 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2936. Min Act: -0.1700
Data Index: 3136746 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3249. Min Act: -0.1700
Data Index: 3136764 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2936. Min Act: -0.1700
Data Index: 3136741 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2623. Min Act: -0.1700
Data Index: 5598342 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2311. Min Act: -0.1700
Data Index: 2959047 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2311. Min Act: -0.1700
Data Index: 3136770 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19