Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.8489. Min Act: -0.1700
Data Index: 499903 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.8177. Min Act: -0.1700
Data Index: 7728 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.8177. Min Act: -0.1700
Data Index: 1145201 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 748446 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7864. Min Act: -0.1700
Data Index: 53401 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7864. Min Act: -0.1700
Data Index: 250989 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7239. Min Act: -0.1700
Data Index: 396892 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 405190 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7864. Min Act: -0.1700
Data Index: 1049351 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7239. Min Act: -0.1700
Data Index: 637414 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 1327649 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 590879 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 1267555 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 561436 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7239. Min Act: -0.1700
Data Index: 1082980 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7239. Min Act: -0.1700
Data Index: 537256 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7551. Min Act: -0.1700
Data Index: 236381 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7239. Min Act: -0.1700
Data Index: 684332 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.6926. Min Act: -0.1700
Data Index: 484925 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8489. Min Range: -4.8489
Max Act: 4.7239. Min Act: -0.1700
Data Index: 56145 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19