Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 970 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.7638. Min Act: -0.1700
Data Index: 424160 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.6999. Min Act: -0.1700
Data Index: 96650 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.6679. Min Act: -0.1700
Data Index: 291120 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.6197. Min Act: -0.1700
Data Index: 293413 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5876. Min Act: -0.1700
Data Index: 744964 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5714. Min Act: -0.1700
Data Index: 480921 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5714. Min Act: -0.1700
Data Index: 434658 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5392. Min Act: -0.1700
Data Index: 544621 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5392. Min Act: -0.1700
Data Index: 565696 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5230. Min Act: -0.1700
Data Index: 110585 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4906. Min Act: -0.1700
Data Index: 868150 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4906. Min Act: -0.1700
Data Index: 954012 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.5068. Min Act: -0.1700
Data Index: 1275560 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4906. Min Act: -0.1700
Data Index: 538553 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4906. Min Act: -0.1700
Data Index: 909620 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4744. Min Act: -0.1700
Data Index: 366771 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4582. Min Act: -0.1700
Data Index: 462815 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4744. Min Act: -0.1700
Data Index: 620993 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4744. Min Act: -0.1700
Data Index: 123416 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7638. Min Range: -2.7638
Max Act: 2.4744. Min Act: -0.1700
Data Index: 673248 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19