Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5084 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2022. Min Range: -6.2022
Max Act: 6.2022. Min Act: -0.1700
Data Index: 5216024 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2022. Min Range: -6.2022
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7333046 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2022. Min Range: -6.2022
Max Act: 6.0147. Min Act: -0.1700
Data Index: 658130 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2022. Min Range: -6.2022
Max Act: 6.0147. Min Act: -0.1700
Data Index: 2471826 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2022. Min Range: -6.2022
Max Act: 6.0147. Min Act: -0.1700
Data Index: 6420048 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.9522. Min Act: -0.1700
Data Index: 5810957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.9522. Min Act: -0.1700
Data Index: 7113719 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.9209. Min Act: -0.1700
Data Index: 6189387 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.9209. Min Act: -0.1700
Data Index: 4219815 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1459986 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 3184075 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 4762776 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 6420977 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 2263619 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1261417 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1633908 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 2174960 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1529499 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8584. Min Act: -0.1700
Data Index: 4828017 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2022. Min Range: -6.2022
Max Act: 5.8584. Min Act: -0.1700
Data Index: 649403 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19