Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 106 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.1513. Min Act: -0.1700
Data Index: 620270 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.1179. Min Act: -0.1700
Data Index: 985721 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.1179. Min Act: -0.1700
Data Index: 828111 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0845. Min Act: -0.1700
Data Index: 264825 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0677. Min Act: -0.1695
Data Index: 55170 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0677. Min Act: -0.1700
Data Index: 689515 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0677. Min Act: -0.1700
Data Index: 22807 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0677. Min Act: -0.1700
Data Index: 1176788 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0677. Min Act: -0.1699
Data Index: 1011725 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0677. Min Act: -0.1700
Data Index: 620166 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0341. Min Act: -0.1700
Data Index: 653989 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0341. Min Act: -0.1700
Data Index: 910525 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0341. Min Act: -0.1700
Data Index: 269204 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1700
Data Index: 1346091 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1700
Data Index: 555907 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1700
Data Index: 714471 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1699
Data Index: 608542 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1700
Data Index: 644938 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1700
Data Index: 953515 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1513. Min Range: -2.1513
Max Act: 2.0172. Min Act: -0.1699
Data Index: 932080 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19