Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1032 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.6001. Min Act: -0.1700
Data Index: 1147946 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.2876. Min Act: -0.1700
Data Index: 5620338 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.2563. Min Act: -0.1700
Data Index: 2184211 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.1313. Min Act: -0.1700
Data Index: 771370 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.1626. Min Act: -0.1700
Data Index: 5492755 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.0688. Min Act: -0.1700
Data Index: 5639222 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.0376. Min Act: -0.1700
Data Index: 1556714 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.0688. Min Act: -0.1700
Data Index: 3205893 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6001. Min Range: -6.6001
Max Act: 6.1001. Min Act: -0.1700
Data Index: 4967094 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.9438. Min Act: -0.1700
Data Index: 3327061 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.9438. Min Act: -0.1700
Data Index: 3026082 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.9126. Min Act: -0.1700
Data Index: 3704785 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.9126. Min Act: -0.1700
Data Index: 3820819 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.8188. Min Act: -0.1700
Data Index: 6258644 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.8501. Min Act: -0.1700
Data Index: 8138477 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.7563. Min Act: -0.1700
Data Index: 1726764 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6259012 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.6938. Min Act: -0.1700
Data Index: 8412984 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.7251. Min Act: -0.1700
Data Index: 2211399 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6001. Min Range: -6.6001
Max Act: 5.6626. Min Act: -0.1700
Data Index: 2569510 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19