Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.9333. Min Act: -0.1700
Data Index: 2704975 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.8395. Min Act: -0.1700
Data Index: 2066363 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.8083. Min Act: -0.1700
Data Index: 227202 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.8083. Min Act: -0.1700
Data Index: 3279432 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.8083. Min Act: -0.1700
Data Index: 6798754 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.8083. Min Act: -0.1700
Data Index: 3999975 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.7458. Min Act: -0.1700
Data Index: 5761206 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.7458. Min Act: -0.1700
Data Index: 3828477 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.7458. Min Act: -0.1700
Data Index: 7434206 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6833. Min Act: -0.1700
Data Index: 8727060 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6520. Min Act: -0.1700
Data Index: 7848462 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6520. Min Act: -0.1700
Data Index: 7214823 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 8262943 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 4919543 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 265603 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 7432101 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 4501901 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 7991447 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.6208. Min Act: -0.1700
Data Index: 7691373 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9333. Min Range: -4.9333
Max Act: 4.5895. Min Act: -0.1700
Data Index: 2773553 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19