Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 293 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.7122. Min Act: -0.1700
Data Index: 445680 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.6809. Min Act: -0.1700
Data Index: 932409 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.5559. Min Act: -0.1700
Data Index: 115460 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.4622. Min Act: -0.1700
Data Index: 965775 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.4309. Min Act: -0.1700
Data Index: 1284522 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.4309. Min Act: -0.1700
Data Index: 176490 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.5559. Min Act: -0.1700
Data Index: 26800 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.4309. Min Act: -0.1700
Data Index: 620941 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.3528. Min Act: -0.1700
Data Index: 134773 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.3684. Min Act: -0.1700
Data Index: 460798 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.3528. Min Act: -0.1700
Data Index: 561177 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.3215. Min Act: -0.1700
Data Index: 1276425 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.3059. Min Act: -0.1700
Data Index: 127581 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2903. Min Act: -0.1700
Data Index: 1169785 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2747. Min Act: -0.1700
Data Index: 817923 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2590. Min Act: -0.1700
Data Index: 359640 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2278. Min Act: -0.1700
Data Index: 969892 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2590. Min Act: -0.1700
Data Index: 916993 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2278. Min Act: -0.1700
Data Index: 1240196 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7122. Min Range: -4.7122
Max Act: 4.2434. Min Act: -0.1700
Data Index: 1153091 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19