Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1814 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.6763. Min Act: -0.1700
Data Index: 885564 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.6763. Min Act: -0.1700
Data Index: 629674 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.6282. Min Act: -0.1700
Data Index: 187875 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.6282. Min Act: -0.1700
Data Index: 450066 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.6442. Min Act: -0.1700
Data Index: 100910 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 548390 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5799. Min Act: -0.1700
Data Index: 868188 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 777736 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 861566 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 894301 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 347517 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 661335 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 700944 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5960. Min Act: -0.1700
Data Index: 1162912 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5638. Min Act: -0.1700
Data Index: 627554 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5799. Min Act: -0.1700
Data Index: 1017518 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5638. Min Act: -0.1700
Data Index: 852025 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5799. Min Act: -0.1700
Data Index: 224113 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5799. Min Act: -0.1700
Data Index: 162933 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6763. Min Range: -2.6763
Max Act: 2.5799. Min Act: -0.1700
Data Index: 490806 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19