Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1016 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 9.3078. Min Range: -9.3078
Max Act: 9.3078. Min Act: -0.1700
Data Index: 959585 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3078. Min Range: -9.3078
Max Act: 9.1203. Min Act: -0.1700
Data Index: 37753 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3078. Min Range: -9.3078
Max Act: 9.0578. Min Act: -0.1700
Data Index: 369433 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3078. Min Range: -9.3078
Max Act: 9.0578. Min Act: -0.1700
Data Index: 307703 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.9953. Min Act: -0.1700
Data Index: 279964 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.9328. Min Act: -0.1700
Data Index: 774978 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8703. Min Act: -0.1700
Data Index: 137113 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.9328. Min Act: -0.1700
Data Index: 1064888 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8703. Min Act: -0.1700
Data Index: 843979 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8703. Min Act: -0.1700
Data Index: 551971 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8703. Min Act: -0.1700
Data Index: 422300 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8703. Min Act: -0.1700
Data Index: 1323575 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8078. Min Act: -0.1700
Data Index: 1262938 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8703. Min Act: -0.1700
Data Index: 698205 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.7453. Min Act: -0.1700
Data Index: 373174 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8078. Min Act: -0.1700
Data Index: 1215085 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8078. Min Act: -0.1700
Data Index: 744886 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.7453. Min Act: -0.1700
Data Index: 348881 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.6828. Min Act: -0.1700
Data Index: 412313 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3078. Min Range: -9.3078
Max Act: 8.8078. Min Act: -0.1700
Data Index: 1037382 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19