Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5116 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2626. Min Act: -0.1700
Data Index: 4358741 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2501. Min Act: -0.1684
Data Index: 2018061 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2439. Min Act: -0.1687
Data Index: 5641167 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2378. Min Act: -0.1697
Data Index: 6118025 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2378. Min Act: -0.1659
Data Index: 7587823 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2317. Min Act: -0.1700
Data Index: 6456180 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2197. Min Act: -0.1685
Data Index: 8591071 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2317. Min Act: -0.1700
Data Index: 2633751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2197. Min Act: -0.1700
Data Index: 476046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2197. Min Act: -0.1690
Data Index: 8138322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2078. Min Act: -0.1693
Data Index: 5294803 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.2078. Min Act: -0.1696
Data Index: 2892591 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1680
Data Index: 1269299 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1665
Data Index: 796423 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1639
Data Index: 2918103 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1700
Data Index: 2446389 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1639
Data Index: 1575917 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1700
Data Index: 2575844 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1696
Data Index: 2554441 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2626. Min Range: -0.2626
Max Act: 0.1961. Min Act: -0.1700
Data Index: 4140837 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19