Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.4571. Min Act: -0.1700
Data Index: 6989764 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.4571. Min Act: -0.1700
Data Index: 5958694 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.3946. Min Act: -0.1700
Data Index: 183935 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.3009. Min Act: -0.1700
Data Index: 2090341 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.2384. Min Act: -0.1700
Data Index: 2360364 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.2384. Min Act: -0.1700
Data Index: 7318240 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.2071. Min Act: -0.1700
Data Index: 1233952 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.2071. Min Act: -0.1700
Data Index: 2611564 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.2071. Min Act: -0.1700
Data Index: 5840520 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.2071. Min Act: -0.1700
Data Index: 155594 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.1759. Min Act: -0.1700
Data Index: 2262695 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.1759. Min Act: -0.1700
Data Index: 4621076 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.1446. Min Act: -0.1700
Data Index: 4021541 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.1446. Min Act: -0.1700
Data Index: 4177621 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.1446. Min Act: -0.1700
Data Index: 8625652 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.1134. Min Act: -0.1700
Data Index: 5311217 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.0508. Min Act: -0.1700
Data Index: 7822409 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.0821. Min Act: -0.1700
Data Index: 8431249 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.0821. Min Act: -0.1700
Data Index: 4114444 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4571. Min Range: -4.4571
Max Act: 4.0508. Min Act: -0.1700
Data Index: 6493184 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19