Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.8373. Min Act: -0.1700
Data Index: 5075560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.8373. Min Act: -0.1700
Data Index: 5285401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7513. Min Act: -0.1700
Data Index: 3145247 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7426. Min Act: -0.1700
Data Index: 7524084 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7426. Min Act: -0.1700
Data Index: 7245880 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7253. Min Act: -0.1700
Data Index: 3341634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7167. Min Act: -0.1700
Data Index: 4119181 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7080. Min Act: -0.1679
Data Index: 4119180 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.7080. Min Act: -0.1700
Data Index: 2356291 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6907. Min Act: -0.1700
Data Index: 5748262 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6993. Min Act: -0.1700
Data Index: 6786854 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6993. Min Act: -0.1700
Data Index: 6116934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6820. Min Act: -0.1700
Data Index: 8708078 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6907. Min Act: -0.1700
Data Index: 7351809 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6907. Min Act: -0.1700
Data Index: 5618362 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6646. Min Act: -0.1700
Data Index: 3484939 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6646. Min Act: -0.1699
Data Index: 8482167 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6820. Min Act: -0.1700
Data Index: 2120392 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6820. Min Act: -0.1700
Data Index: 4210010 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8373. Min Range: -1.8373
Max Act: 1.6820. Min Act: -0.1700
Data Index: 7457361 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19