Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5028 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.6024. Min Act: -0.1700
Data Index: 3319483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.5087. Min Act: -0.1700
Data Index: 8293552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.4774. Min Act: -0.1700
Data Index: 190961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.4462. Min Act: -0.1700
Data Index: 1664114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.4462. Min Act: -0.1700
Data Index: 6192788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.4149. Min Act: -0.1700
Data Index: 5870259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3837. Min Act: -0.1700
Data Index: 8533906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.4149. Min Act: -0.1700
Data Index: 6336307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3524. Min Act: -0.1700
Data Index: 2846831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3837. Min Act: -0.1700
Data Index: 6140788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3837. Min Act: -0.1700
Data Index: 6219689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3524. Min Act: -0.1700
Data Index: 5778015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3524. Min Act: -0.1700
Data Index: 4723680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3524. Min Act: -0.1700
Data Index: 7169848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3524. Min Act: -0.1700
Data Index: 7548241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3524. Min Act: -0.1700
Data Index: 7362611 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3212. Min Act: -0.1700
Data Index: 4559276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.2899. Min Act: -0.1700
Data Index: 715727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.2899. Min Act: -0.1700
Data Index: 7349593 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6024. Min Range: -4.6024
Max Act: 4.3212. Min Act: -0.1700
Data Index: 441683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19