Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 174 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.3449. Min Act: -0.1700
Data Index: 76929 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.3135. Min Act: -0.1700
Data Index: 181461 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.3135. Min Act: -0.1700
Data Index: 271956 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2821. Min Act: -0.1700
Data Index: 974318 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2978. Min Act: -0.1700
Data Index: 726177 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2663. Min Act: -0.1700
Data Index: 1200051 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2506. Min Act: -0.1700
Data Index: 824164 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2506. Min Act: -0.1700
Data Index: 366456 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2506. Min Act: -0.1700
Data Index: 26516 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2663. Min Act: -0.1700
Data Index: 536346 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2663. Min Act: -0.1700
Data Index: 906187 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2192. Min Act: -0.1700
Data Index: 675123 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2192. Min Act: -0.1700
Data Index: 1068420 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.1877. Min Act: -0.1700
Data Index: 1460189 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.1877. Min Act: -0.1700
Data Index: 49245 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.1877. Min Act: -0.1700
Data Index: 86683 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.1720. Min Act: -0.1700
Data Index: 1199856 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.2035. Min Act: -0.1700
Data Index: 850055 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.1877. Min Act: -0.1700
Data Index: 1025451 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3449. Min Range: -3.3449
Max Act: 3.1720. Min Act: -0.1700
Data Index: 94851 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19