Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3967 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.8886. Min Act: -0.1700
Data Index: 1850763 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.7948. Min Act: -0.1700
Data Index: 8228895 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.8261. Min Act: -0.1700
Data Index: 3283304 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.7948. Min Act: -0.1700
Data Index: 127979 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3960648 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.7323. Min Act: -0.1700
Data Index: 5236257 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.6698. Min Act: -0.1700
Data Index: 3463087 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1857183 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.5448. Min Act: -0.1700
Data Index: 2416548 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.4823. Min Act: -0.1700
Data Index: 4040933 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3886. Min Act: -0.1700
Data Index: 43452 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3886. Min Act: -0.1700
Data Index: 3627906 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3573. Min Act: -0.1700
Data Index: 4799288 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3261. Min Act: -0.1700
Data Index: 1533603 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3886. Min Act: -0.1700
Data Index: 1834697 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3573. Min Act: -0.1700
Data Index: 4483243 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.2948. Min Act: -0.1700
Data Index: 6926029 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3261. Min Act: -0.1700
Data Index: 1684665 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.3261. Min Act: -0.1700
Data Index: 7923950 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8886. Min Range: -5.8886
Max Act: 5.2948. Min Act: -0.1700
Data Index: 756122 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19