Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1410. Min Range: -6.1410
Max Act: 6.1410. Min Act: -0.1700
Data Index: 2623870 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.9848. Min Act: -0.1700
Data Index: 8643572 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.9848. Min Act: -0.1700
Data Index: 1050468 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.9848. Min Act: -0.1700
Data Index: 1380849 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.9535. Min Act: -0.1700
Data Index: 5835668 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.9535. Min Act: -0.1700
Data Index: 5943465 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.9223. Min Act: -0.1700
Data Index: 495529 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.8910. Min Act: -0.1700
Data Index: 5258064 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.8910. Min Act: -0.1700
Data Index: 8451270 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.8285. Min Act: -0.1700
Data Index: 3737838 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7973. Min Act: -0.1700
Data Index: 8110532 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7973. Min Act: -0.1700
Data Index: 902988 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 969306 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7973. Min Act: -0.1700
Data Index: 5099109 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 6741505 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 8139352 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 3972833 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1233306 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 132400 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1410. Min Range: -6.1410
Max Act: 5.7660. Min Act: -0.1700
Data Index: 7822390 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19