Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.4235. Min Act: -0.1700
Data Index: 4355654 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0797. Min Act: -0.1700
Data Index: 6848769 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0172. Min Act: -0.1700
Data Index: 6848768 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9859. Min Act: -0.1700
Data Index: 1704583 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9547. Min Act: -0.1700
Data Index: 5296720 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9547. Min Act: -0.1700
Data Index: 512950 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9859. Min Act: -0.1700
Data Index: 3298775 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9234. Min Act: -0.1700
Data Index: 1578003 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8921. Min Act: -0.1700
Data Index: 3163613 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8296. Min Act: -0.1700
Data Index: 4355658 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8609. Min Act: -0.1700
Data Index: 2650273 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8609. Min Act: -0.1700
Data Index: 6848775 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8609. Min Act: -0.1700
Data Index: 3531831 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8609. Min Act: -0.1700
Data Index: 3991348 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8296. Min Act: -0.1700
Data Index: 4733105 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8296. Min Act: -0.1700
Data Index: 7452883 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.8296. Min Act: -0.1700
Data Index: 3991349 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.7983. Min Act: -0.1700
Data Index: 4986996 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.7983. Min Act: -0.1700
Data Index: 4076971 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.7670. Min Act: -0.1700
Data Index: 5150072 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19