Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1410. Min Range: -4.1410
Max Act: 4.1410. Min Act: -0.1700
Data Index: 7539186 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1410. Min Range: -4.1410
Max Act: 4.0785. Min Act: -0.1700
Data Index: 3192470 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9847. Min Act: -0.1700
Data Index: 7835415 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1410. Min Range: -4.1410
Max Act: 4.0160. Min Act: -0.1700
Data Index: 4866930 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9847. Min Act: -0.1700
Data Index: 2511429 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9847. Min Act: -0.1700
Data Index: 7366493 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9535. Min Act: -0.1700
Data Index: 7791801 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9535. Min Act: -0.1700
Data Index: 4519821 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9378. Min Act: -0.1700
Data Index: 5099448 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9378. Min Act: -0.1700
Data Index: 6539766 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.9066. Min Act: -0.1700
Data Index: 6475077 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8753. Min Act: -0.1700
Data Index: 121167 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8753. Min Act: -0.1700
Data Index: 5971864 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8909. Min Act: -0.1700
Data Index: 1068550 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8440. Min Act: -0.1700
Data Index: 5415048 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8440. Min Act: -0.1700
Data Index: 7084549 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8440. Min Act: -0.1700
Data Index: 3262853 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8284. Min Act: -0.1700
Data Index: 4020698 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8284. Min Act: -0.1700
Data Index: 1089310 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1410. Min Range: -4.1410
Max Act: 3.8440. Min Act: -0.1700
Data Index: 3535559 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19