Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2018 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.2167. Min Act: -0.1700
Data Index: 59415 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.2167. Min Act: -0.1700
Data Index: 215081 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1229. Min Act: -0.1700
Data Index: 704814 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1854. Min Act: -0.1700
Data Index: 1092731 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1542. Min Act: -0.1700
Data Index: 586833 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1229. Min Act: -0.1700
Data Index: 1128559 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1229. Min Act: -0.1700
Data Index: 156678 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1229. Min Act: -0.1700
Data Index: 723249 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0917. Min Act: -0.1700
Data Index: 1021540 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0917. Min Act: -0.1700
Data Index: 796717 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0292. Min Act: -0.1700
Data Index: 998510 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0917. Min Act: -0.1700
Data Index: 1107023 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0292. Min Act: -0.1700
Data Index: 1048929 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0292. Min Act: -0.1700
Data Index: 370870 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0604. Min Act: -0.1700
Data Index: 797325 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2167. Min Range: -6.2167
Max Act: 5.9979. Min Act: -0.1700
Data Index: 398597 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.1229. Min Act: -0.1700
Data Index: 409022 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0604. Min Act: -0.1700
Data Index: 241030 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2167. Min Range: -6.2167
Max Act: 5.9667. Min Act: -0.1700
Data Index: 890124 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2167. Min Range: -6.2167
Max Act: 6.0604. Min Act: -0.1700
Data Index: 32995 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19