Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.9756. Min Act: -0.1700
Data Index: 6439672 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.9417. Min Act: -0.1700
Data Index: 5773118 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8906. Min Act: -0.1700
Data Index: 7154048 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8564. Min Act: -0.1700
Data Index: 4170238 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8564. Min Act: -0.1700
Data Index: 590606 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 7257769 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 877259 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8392. Min Act: -0.1700
Data Index: 6045476 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8392. Min Act: -0.1700
Data Index: 5054336 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8392. Min Act: -0.1700
Data Index: 7101281 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 4717298 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 2342210 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 6937019 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 1032479 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 7003784 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 4967493 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 3514936 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 7289534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 4072441 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9756. Min Range: -1.9756
Max Act: 1.8221. Min Act: -0.1700
Data Index: 7289531 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19