Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.6113. Min Act: -0.1700
Data Index: 825337 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.4551. Min Act: -0.1700
Data Index: 5622215 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3613. Min Act: -0.1700
Data Index: 1776229 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3301. Min Act: -0.1700
Data Index: 3080595 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3301. Min Act: -0.1700
Data Index: 1082038 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2676. Min Act: -0.1700
Data Index: 1202367 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2363. Min Act: -0.1700
Data Index: 3375132 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2051. Min Act: -0.1700
Data Index: 1478747 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2363. Min Act: -0.1700
Data Index: 5863153 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1426. Min Act: -0.1700
Data Index: 1547656 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1738. Min Act: -0.1700
Data Index: 2325110 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1738. Min Act: -0.1700
Data Index: 4834863 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1738. Min Act: -0.1700
Data Index: 3013011 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1113. Min Act: -0.1700
Data Index: 8590059 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1113. Min Act: -0.1700
Data Index: 6993586 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1113. Min Act: -0.1700
Data Index: 481116 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.0801. Min Act: -0.1700
Data Index: 6311869 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.0488. Min Act: -0.1700
Data Index: 2685930 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.1113. Min Act: -0.1700
Data Index: 5564122 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.0801. Min Act: -0.1700
Data Index: 5565466 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19