Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 153 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.9811. Min Act: -0.1700
Data Index: 1204557 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0124. Min Range: -4.0124
Max Act: 4.0124. Min Act: -0.1700
Data Index: 1424852 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.9186. Min Act: -0.1700
Data Index: 974776 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.9498. Min Act: -0.1700
Data Index: 139347 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.9186. Min Act: -0.1700
Data Index: 705832 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 688549 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8873. Min Act: -0.1700
Data Index: 465252 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8873. Min Act: -0.1700
Data Index: 1086875 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8873. Min Act: -0.1700
Data Index: 1336683 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.7935. Min Act: -0.1700
Data Index: 208423 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.9186. Min Act: -0.1700
Data Index: 789486 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 1143720 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 1643822 (Python Code)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8873. Min Act: -0.1700
Data Index: 1463044 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 1542595 (Python Code)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 1405969 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 166982 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8873. Min Act: -0.1700
Data Index: 543075 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8873. Min Act: -0.1700
Data Index: 792541 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0124. Min Range: -4.0124
Max Act: 3.8560. Min Act: -0.1700
Data Index: 1126220 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19