Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2030 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.6037. Min Act: -0.1700
Data Index: 887912 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5876. Min Act: -0.1700
Data Index: 302174 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5876. Min Act: -0.1700
Data Index: 1065191 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5876. Min Act: -0.1700
Data Index: 306769 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5715. Min Act: -0.1700
Data Index: 1523122 (Python Code)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5876. Min Act: -0.1700
Data Index: 119863 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5876. Min Act: -0.1700
Data Index: 533797 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5876. Min Act: -0.1700
Data Index: 914030 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5715. Min Act: -0.1700
Data Index: 1209190 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 491492 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5715. Min Act: -0.1700
Data Index: 1112466 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5715. Min Act: -0.1700
Data Index: 1437102 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5715. Min Act: -0.1700
Data Index: 1533951 (Python Code)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 1564498 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 144529 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5392. Min Act: -0.1700
Data Index: 623989 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 1233081 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 465237 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 246627 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6037. Min Range: -2.6037
Max Act: 2.5554. Min Act: -0.1700
Data Index: 124566 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19