Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.8048. Min Act: -0.1700
Data Index: 1042331 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7422. Min Act: -0.1700
Data Index: 700963 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7422. Min Act: -0.1700
Data Index: 820391 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7266. Min Act: -0.1700
Data Index: 1292712 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7266. Min Act: -0.1700
Data Index: 390713 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7266. Min Act: -0.1700
Data Index: 1345439 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7266. Min Act: -0.1700
Data Index: 1099191 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7422. Min Act: -0.1700
Data Index: 1313947 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7266. Min Act: -0.1700
Data Index: 515721 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7109. Min Act: -0.1700
Data Index: 423556 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7109. Min Act: -0.1700
Data Index: 1317978 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7266. Min Act: -0.1700
Data Index: 902045 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.7109. Min Act: -0.1700
Data Index: 1159460 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6796. Min Act: -0.1700
Data Index: 936121 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6796. Min Act: -0.1700
Data Index: 191875 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6640. Min Act: -0.1700
Data Index: 262665 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6640. Min Act: -0.1700
Data Index: 583454 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6640. Min Act: -0.1700
Data Index: 453795 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6796. Min Act: -0.1700
Data Index: 349840 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6953. Min Act: -0.1700
Data Index: 865781 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19