Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1637. Min Range: -8.1637
Max Act: 8.1637. Min Act: -0.1700
Data Index: 1351341 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.9450. Min Act: -0.1700
Data Index: 4252227 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.8825. Min Act: -0.1700
Data Index: 7331751 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.8512. Min Act: -0.1700
Data Index: 4536379 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.6950. Min Act: -0.1700
Data Index: 3490012 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.5700. Min Act: -0.1700
Data Index: 5928875 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.5700. Min Act: -0.1700
Data Index: 3500613 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.5387. Min Act: -0.1700
Data Index: 1236716 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.4762. Min Act: -0.1700
Data Index: 5798840 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.5387. Min Act: -0.1700
Data Index: 73430 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.4762. Min Act: -0.1700
Data Index: 6449965 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.4762. Min Act: -0.1700
Data Index: 2033576 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.4450. Min Act: -0.1700
Data Index: 7535516 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.4137. Min Act: -0.1700
Data Index: 2083653 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.3512. Min Act: -0.1700
Data Index: 7937503 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.3512. Min Act: -0.1700
Data Index: 8677433 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.3200. Min Act: -0.1700
Data Index: 1629954 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.2887. Min Act: -0.1700
Data Index: 5929110 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.3200. Min Act: -0.1700
Data Index: 6541481 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1637. Min Range: -8.1637
Max Act: 7.3200. Min Act: -0.1700
Data Index: 3719988 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19