Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 7 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.4145. Min Act: -0.1700
Data Index: 889696 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.3520. Min Act: -0.1700
Data Index: 1079060 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.2582. Min Act: -0.1700
Data Index: 1171144 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1645. Min Act: -0.1700
Data Index: 426752 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.0082. Min Act: -0.1700
Data Index: 867075 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1645. Min Act: -0.1700
Data Index: 1287329 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1645. Min Act: -0.1700
Data Index: 131179 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1645. Min Act: -0.1700
Data Index: 794504 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1332. Min Act: -0.1700
Data Index: 49314 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4145. Min Range: -8.4145
Max Act: 7.8832. Min Act: -0.1700
Data Index: 421027 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1332. Min Act: -0.1700
Data Index: 787961 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1332. Min Act: -0.1700
Data Index: 1225529 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.0707. Min Act: -0.1700
Data Index: 996612 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1332. Min Act: -0.1700
Data Index: 1103387 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.0707. Min Act: -0.1700
Data Index: 377251 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4145. Min Range: -8.4145
Max Act: 7.8832. Min Act: -0.1700
Data Index: 1253478 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1020. Min Act: -0.1700
Data Index: 232706 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4145. Min Range: -8.4145
Max Act: 8.1332. Min Act: -0.1700
Data Index: 946463 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4145. Min Range: -8.4145
Max Act: 7.9457. Min Act: -0.1700
Data Index: 1217736 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4145. Min Range: -8.4145
Max Act: 7.9457. Min Act: -0.1700
Data Index: 1138836 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19