Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1508 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.6299. Min Act: -0.1700
Data Index: 254685 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.5171. Min Act: -0.1700
Data Index: 1247814 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4847. Min Act: -0.1700
Data Index: 767355 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4847. Min Act: -0.1700
Data Index: 1318808 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4847. Min Act: -0.1700
Data Index: 132480 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4522. Min Act: -0.1700
Data Index: 527588 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4197. Min Act: -0.1700
Data Index: 1183261 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4522. Min Act: -0.1700
Data Index: 1133837 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4359. Min Act: -0.1700
Data Index: 1064882 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4197. Min Act: -0.1700
Data Index: 1166943 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4034. Min Act: -0.1700
Data Index: 187138 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4197. Min Act: -0.1700
Data Index: 1316625 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4197. Min Act: -0.1700
Data Index: 662885 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4359. Min Act: -0.1700
Data Index: 161214 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4034. Min Act: -0.1700
Data Index: 679959 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4034. Min Act: -0.1700
Data Index: 1106658 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4034. Min Act: -0.1700
Data Index: 577947 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4034. Min Act: -0.1700
Data Index: 30778 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.3871. Min Act: -0.1700
Data Index: 629761 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6299. Min Range: -2.6299
Max Act: 2.4034. Min Act: -0.1700
Data Index: 601388 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19