Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.3462. Min Act: -0.1700
Data Index: 7078300 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.1899. Min Act: -0.1700
Data Index: 1627446 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.2212. Min Act: -0.1700
Data Index: 428284 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.1586. Min Act: -0.1700
Data Index: 7078287 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.1586. Min Act: -0.1700
Data Index: 7078286 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.1586. Min Act: -0.1700
Data Index: 6562699 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.1899. Min Act: -0.1700
Data Index: 4445713 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.1274. Min Act: -0.1700
Data Index: 4445714 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.0961. Min Act: -0.1700
Data Index: 6243632 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.0649. Min Act: -0.1700
Data Index: 4249808 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.0336. Min Act: -0.1700
Data Index: 7078301 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.9711. Min Act: -0.1700
Data Index: 7078282 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.9711. Min Act: -0.1700
Data Index: 4445715 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.9398. Min Act: -0.1700
Data Index: 5074300 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.9398. Min Act: -0.1700
Data Index: 8297853 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3462. Min Range: -4.3462
Max Act: 4.0024. Min Act: -0.1700
Data Index: 7078299 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.9242. Min Act: -0.1700
Data Index: 428289 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.8617. Min Act: -0.1700
Data Index: 3315222 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.8617. Min Act: -0.1700
Data Index: 1018837 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3462. Min Range: -4.3462
Max Act: 3.8773. Min Act: -0.1700
Data Index: 2956999 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19