Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4023. Min Range: -10.4023
Max Act: 10.4023. Min Act: -0.1700
Data Index: 5088004 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4023. Min Range: -10.4023
Max Act: 10.0898. Min Act: -0.1700
Data Index: 7103647 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4023. Min Range: -10.4023
Max Act: 10.0273. Min Act: -0.1700
Data Index: 4203245 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.9023. Min Act: -0.1700
Data Index: 2437105 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.7773. Min Act: -0.1700
Data Index: 5150300 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.7148. Min Act: -0.1700
Data Index: 4027632 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.6523. Min Act: -0.1700
Data Index: 2207934 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5898. Min Act: -0.1700
Data Index: 7673702 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5898. Min Act: -0.1700
Data Index: 4759776 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5898. Min Act: -0.1700
Data Index: 510944 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5898. Min Act: -0.1700
Data Index: 1901526 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5273. Min Act: -0.1700
Data Index: 8783484 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5273. Min Act: -0.1700
Data Index: 29949 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5273. Min Act: -0.1700
Data Index: 1522876 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5898. Min Act: -0.1700
Data Index: 1573961 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5273. Min Act: -0.1700
Data Index: 5822244 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.4648. Min Act: -0.1700
Data Index: 1689956 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.5273. Min Act: -0.1700
Data Index: 1909895 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.4648. Min Act: -0.1700
Data Index: 1540754 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4023. Min Range: -10.4023
Max Act: 9.4648. Min Act: -0.1700
Data Index: 4896929 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19