Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6833. Min Act: -0.1700
Data Index: 4605796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6513. Min Act: -0.1700
Data Index: 7681938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6352. Min Act: -0.1700
Data Index: 2366271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6352. Min Act: -0.1700
Data Index: 1763445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6352. Min Act: -0.1700
Data Index: 1976702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6191. Min Act: -0.1700
Data Index: 2769861 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6191. Min Act: -0.1700
Data Index: 6986925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 6867841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 2708804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 5282885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 4776499 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6191. Min Act: -0.1700
Data Index: 285437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 7093887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 2844606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.6031. Min Act: -0.1700
Data Index: 1497062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.5870. Min Act: -0.1700
Data Index: 4502525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.5870. Min Act: -0.1700
Data Index: 4935378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.5708. Min Act: -0.1700
Data Index: 859653 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.5870. Min Act: -0.1700
Data Index: 6536720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6833. Min Range: -2.6833
Max Act: 2.5708. Min Act: -0.1700
Data Index: 1184628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19