Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 35 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.1098. Min Act: -0.1700
Data Index: 302370 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0316. Min Act: -0.1700
Data Index: 1129398 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0629. Min Act: -0.1700
Data Index: 55163 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0316. Min Act: -0.1700
Data Index: 1048739 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0160. Min Act: -0.1700
Data Index: 856365 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0160. Min Act: -0.1700
Data Index: 410194 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9847. Min Act: -0.1700
Data Index: 1263695 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0316. Min Act: -0.1700
Data Index: 338105 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0160. Min Act: -0.1700
Data Index: 317170 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9847. Min Act: -0.1700
Data Index: 1049777 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9847. Min Act: -0.1700
Data Index: 49211 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9691. Min Act: -0.1700
Data Index: 358742 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9847. Min Act: -0.1700
Data Index: 906200 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9378. Min Act: -0.1700
Data Index: 169957 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9691. Min Act: -0.1700
Data Index: 466323 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9378. Min Act: -0.1700
Data Index: 744519 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9222. Min Act: -0.1700
Data Index: 846238 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9535. Min Act: -0.1700
Data Index: 513031 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1098. Min Range: -4.1098
Max Act: 4.0004. Min Act: -0.1700
Data Index: 1017080 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1098. Min Range: -4.1098
Max Act: 3.9222. Min Act: -0.1700
Data Index: 579747 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19