Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 7080616 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 8747312 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 6379648 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4437. Min Act: -0.1700
Data Index: 6701788 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 389034 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4437. Min Act: -0.1700
Data Index: 7912085 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 6322027 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.3499. Min Act: -0.1700
Data Index: 1173922 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.3187. Min Act: -0.1700
Data Index: 5419475 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.2874. Min Act: -0.1700
Data Index: 5569748 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.2874. Min Act: -0.1700
Data Index: 1363762 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.2249. Min Act: -0.1700
Data Index: 7641762 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6659300 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1937. Min Act: -0.1700
Data Index: 4274215 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1624. Min Act: -0.1700
Data Index: 4030524 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1624. Min Act: -0.1700
Data Index: 2338083 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1624. Min Act: -0.1700
Data Index: 6170215 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1312. Min Act: -0.1700
Data Index: 3896160 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.1312. Min Act: -0.1700
Data Index: 2280863 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.0999. Min Act: -0.1700
Data Index: 220764 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19