Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1901 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.1182. Min Act: -0.1700
Data Index: 640972 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0551. Min Act: -0.1700
Data Index: 722917 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0393. Min Act: -0.1700
Data Index: 236222 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0551. Min Act: -0.1700
Data Index: 857527 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0393. Min Act: -0.1700
Data Index: 628950 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0235. Min Act: -0.1700
Data Index: 1278196 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0235. Min Act: -0.1700
Data Index: 396401 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0077. Min Act: -0.1700
Data Index: 604199 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0077. Min Act: -0.1700
Data Index: 1342302 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9761. Min Act: -0.1700
Data Index: 821867 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1182. Min Range: -3.1182
Max Act: 3.0077. Min Act: -0.1700
Data Index: 342438 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9761. Min Act: -0.1700
Data Index: 36598 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9128. Min Act: -0.1700
Data Index: 57060 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9603. Min Act: -0.1700
Data Index: 307239 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9445. Min Act: -0.1700
Data Index: 121044 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9761. Min Act: -0.1700
Data Index: 1005715 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9603. Min Act: -0.1700
Data Index: 211881 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9919. Min Act: -0.1700
Data Index: 1285556 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9603. Min Act: -0.1700
Data Index: 1016579 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1182. Min Range: -3.1182
Max Act: 2.9603. Min Act: -0.1700
Data Index: 4145 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19