Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 91 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.9364. Min Act: -0.1700
Data Index: 150027 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8895. Min Act: -0.1700
Data Index: 1016816 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8738. Min Act: -0.1700
Data Index: 1303819 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8426. Min Act: -0.1700
Data Index: 231451 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8426. Min Act: -0.1700
Data Index: 517805 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8426. Min Act: -0.1700
Data Index: 1100088 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8582. Min Act: -0.1700
Data Index: 761212 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8426. Min Act: -0.1700
Data Index: 1221425 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8113. Min Act: -0.1700
Data Index: 718851 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8269. Min Act: -0.1700
Data Index: 587600 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8113. Min Act: -0.1700
Data Index: 1070895 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8113. Min Act: -0.1700
Data Index: 537048 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8269. Min Act: -0.1700
Data Index: 1184215 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8113. Min Act: -0.1700
Data Index: 1061124 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.7956. Min Act: -0.1700
Data Index: 391150 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8113. Min Act: -0.1700
Data Index: 742601 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.7956. Min Act: -0.1700
Data Index: 389559 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.7956. Min Act: -0.1700
Data Index: 254597 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.7956. Min Act: -0.1700
Data Index: 849994 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9364. Min Range: -3.9364
Max Act: 3.8113. Min Act: -0.1700
Data Index: 661673 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19