Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 409 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.6690. Min Act: -0.1700
Data Index: 1479263 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.6208. Min Act: -0.1700
Data Index: 5737480 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.6208. Min Act: -0.1700
Data Index: 4763688 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5403. Min Act: -0.1700
Data Index: 5711131 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5079. Min Act: -0.1700
Data Index: 2584736 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5241. Min Act: -0.1700
Data Index: 55436 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5079. Min Act: -0.1700
Data Index: 7402197 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5241. Min Act: -0.1700
Data Index: 2437813 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5079. Min Act: -0.1700
Data Index: 5073196 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.5079. Min Act: -0.1700
Data Index: 5655623 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4593. Min Act: -0.1700
Data Index: 2344265 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4593. Min Act: -0.1700
Data Index: 3350800 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4593. Min Act: -0.1700
Data Index: 5574553 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4430. Min Act: -0.1700
Data Index: 8634953 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4430. Min Act: -0.1700
Data Index: 1401204 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4430. Min Act: -0.1700
Data Index: 8518662 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4430. Min Act: -0.1700
Data Index: 6251559 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4430. Min Act: -0.1700
Data Index: 418447 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4593. Min Act: -0.1700
Data Index: 5547031 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6690. Min Range: -2.6690
Max Act: 2.4430. Min Act: -0.1700
Data Index: 8154565 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19