Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2106. Min Range: -10.2106
Max Act: 10.2106. Min Act: -0.1700
Data Index: 1560467 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2106. Min Range: -10.2106
Max Act: 10.0231. Min Act: -0.1700
Data Index: 6999164 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.9606. Min Act: -0.1700
Data Index: 2181664 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.9606. Min Act: -0.1700
Data Index: 1845676 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.8981. Min Act: -0.1700
Data Index: 2340855 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.9606. Min Act: -0.1700
Data Index: 7410026 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.8981. Min Act: -0.1700
Data Index: 966372 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.8356. Min Act: -0.1700
Data Index: 1251261 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7731. Min Act: -0.1700
Data Index: 5167485 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7731. Min Act: -0.1700
Data Index: 3828795 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7731. Min Act: -0.1700
Data Index: 8449081 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7731. Min Act: -0.1700
Data Index: 173896 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7731. Min Act: -0.1700
Data Index: 8827059 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7731. Min Act: -0.1700
Data Index: 4673950 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.7106. Min Act: -0.1700
Data Index: 2810574 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.5856. Min Act: -0.1700
Data Index: 7323762 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.6481. Min Act: -0.1700
Data Index: 5487645 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.6481. Min Act: -0.1700
Data Index: 5205648 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.6481. Min Act: -0.1700
Data Index: 1209387 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2106. Min Range: -10.2106
Max Act: 9.5856. Min Act: -0.1700
Data Index: 4821280 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19