Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.5427. Min Act: -0.1700
Data Index: 5848762 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.5114. Min Act: -0.1700
Data Index: 4767012 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.5114. Min Act: -0.1700
Data Index: 4748826 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.5114. Min Act: -0.1700
Data Index: 3008345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.5114. Min Act: -0.1700
Data Index: 4159418 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.5114. Min Act: -0.1700
Data Index: 8798128 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 5147359 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 4913494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 477461 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 3986507 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 8815658 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 8321636 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 7606098 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 2964791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 5773235 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4801. Min Act: -0.1700
Data Index: 1492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4487. Min Act: -0.1700
Data Index: 1472557 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4487. Min Act: -0.1700
Data Index: 4422597 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4487. Min Act: -0.1700
Data Index: 1587858 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5427. Min Range: -3.5427
Max Act: 3.4487. Min Act: -0.1700
Data Index: 863679 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19