Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2021 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1690. Min Range: -4.1690
Max Act: 4.1690. Min Act: -0.1700
Data Index: 678837 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1690. Min Range: -4.1690
Max Act: 4.0126. Min Act: -0.1700
Data Index: 979690 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1690. Min Range: -4.1690
Max Act: 4.0752. Min Act: -0.1700
Data Index: 247564 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.9657. Min Act: -0.1700
Data Index: 495129 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.8719. Min Act: -0.1700
Data Index: 392151 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.8563. Min Act: -0.1700
Data Index: 988208 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.8719. Min Act: -0.1700
Data Index: 202682 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.8407. Min Act: -0.1700
Data Index: 147425 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.8094. Min Act: -0.1700
Data Index: 959396 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.8407. Min Act: -0.1700
Data Index: 681946 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7937. Min Act: -0.1700
Data Index: 444579 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7937. Min Act: -0.1700
Data Index: 478176 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7937. Min Act: -0.1700
Data Index: 39597 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7937. Min Act: -0.1700
Data Index: 560982 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7468. Min Act: -0.1700
Data Index: 670142 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7937. Min Act: -0.1700
Data Index: 974330 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7624. Min Act: -0.1700
Data Index: 97121 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7468. Min Act: -0.1700
Data Index: 724020 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7312. Min Act: -0.1700
Data Index: 387055 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1690. Min Range: -4.1690
Max Act: 3.7468. Min Act: -0.1700
Data Index: 754306 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19