Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.7454. Min Act: -0.1700
Data Index: 1961565 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 2747907 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 8365624 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 7434675 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 926850 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 7125178 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 4184022 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 2332402 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 6539620 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 1727278 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 6033209 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 1144597 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 5115854 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 6060196 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 8465169 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 567751 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5266. Min Act: -0.1700
Data Index: 4467762 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5266. Min Act: -0.1700
Data Index: 2859894 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5266. Min Act: -0.1700
Data Index: 1028935 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.4954. Min Act: -0.1700
Data Index: 5282594 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19