Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1986 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3107. Min Range: -4.3107
Max Act: 4.3107. Min Act: -0.1700
Data Index: 179387 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.9669. Min Act: -0.1700
Data Index: 139783 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.9669. Min Act: -0.1700
Data Index: 1049310 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.9043. Min Act: -0.1700
Data Index: 891000 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.9356. Min Act: -0.1700
Data Index: 901595 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.8730. Min Act: -0.1700
Data Index: 598699 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.8418. Min Act: -0.1700
Data Index: 251895 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.8418. Min Act: -0.1700
Data Index: 16219 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.8105. Min Act: -0.1700
Data Index: 745264 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.7792. Min Act: -0.1700
Data Index: 717790 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.7636. Min Act: -0.1700
Data Index: 239405 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.7792. Min Act: -0.1700
Data Index: 385797 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.6697. Min Act: -0.1700
Data Index: 753825 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.6540. Min Act: -0.1700
Data Index: 72776 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.6227. Min Act: -0.1700
Data Index: 931673 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.6697. Min Act: -0.1700
Data Index: 945300 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.6071. Min Act: -0.1700
Data Index: 977334 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.5914. Min Act: -0.1700
Data Index: 417546 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.5914. Min Act: -0.1700
Data Index: 382055 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3107. Min Range: -4.3107
Max Act: 3.5757. Min Act: -0.1700
Data Index: 279227 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19