Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2468 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.6689. Min Act: -0.1700
Data Index: 4142621 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.6368. Min Act: -0.1700
Data Index: 1083280 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5885. Min Act: -0.1700
Data Index: 730571 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5885. Min Act: -0.1700
Data Index: 6776055 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5724. Min Act: -0.1700
Data Index: 4896237 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5724. Min Act: -0.1700
Data Index: 2901072 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5724. Min Act: -0.1700
Data Index: 1491120 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5563. Min Act: -0.1700
Data Index: 1015380 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5724. Min Act: -0.1700
Data Index: 6943035 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5563. Min Act: -0.1700
Data Index: 6295861 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5401. Min Act: -0.1700
Data Index: 1427494 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5240. Min Act: -0.1700
Data Index: 7484100 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5563. Min Act: -0.1700
Data Index: 8424021 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5563. Min Act: -0.1700
Data Index: 602692 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5923299 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5078. Min Act: -0.1700
Data Index: 948679 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5240. Min Act: -0.1700
Data Index: 8020447 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5078. Min Act: -0.1700
Data Index: 8393166 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5240. Min Act: -0.1700
Data Index: 8707817 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6689. Min Range: -2.6689
Max Act: 2.5078. Min Act: -0.1700
Data Index: 5716160 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19