Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5082 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.8809. Min Act: -0.1700
Data Index: 8059672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.8496. Min Act: -0.1700
Data Index: 3946713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.7870. Min Act: -0.1700
Data Index: 8798436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.7245. Min Act: -0.1700
Data Index: 8283252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.7245. Min Act: -0.1700
Data Index: 4122425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6932. Min Act: -0.1699
Data Index: 3013067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6932. Min Act: -0.1700
Data Index: 8802249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6619. Min Act: -0.1700
Data Index: 1842421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6619. Min Act: -0.1700
Data Index: 4921262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6619. Min Act: -0.1700
Data Index: 3431340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 1776683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 48793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6619. Min Act: -0.1700
Data Index: 4767397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 1871362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 7684562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 1632468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 2632359 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.5993. Min Act: -0.1700
Data Index: 7221233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.5993. Min Act: -0.1700
Data Index: 3286746 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8809. Min Range: -3.8809
Max Act: 3.6306. Min Act: -0.1700
Data Index: 2122810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19