Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.9030. Min Act: -0.1700
Data Index: 2238015 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.8405. Min Act: -0.1700
Data Index: 5372354 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.7155. Min Act: -0.1700
Data Index: 2238016 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.6530. Min Act: -0.1700
Data Index: 4098519 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.6217. Min Act: -0.1700
Data Index: 3507702 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.6217. Min Act: -0.1700
Data Index: 2238014 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.6217. Min Act: -0.1700
Data Index: 2771759 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.5592. Min Act: -0.1699
Data Index: 6924390 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.5592. Min Act: -0.1700
Data Index: 2238013 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.5592. Min Act: -0.1700
Data Index: 5233720 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.5280. Min Act: -0.1700
Data Index: 5287950 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.5280. Min Act: -0.1700
Data Index: 2120439 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4967. Min Act: -0.1700
Data Index: 4093988 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4655. Min Act: -0.1700
Data Index: 1709790 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4030. Min Act: -0.1700
Data Index: 3962104 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4342. Min Act: -0.1700
Data Index: 8636535 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4342. Min Act: -0.1700
Data Index: 3659175 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4342. Min Act: -0.1700
Data Index: 1120645 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4342. Min Act: -0.1700
Data Index: 7342860 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9030. Min Range: -6.9030
Max Act: 6.4030. Min Act: -0.1700
Data Index: 3941431 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19