Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 203 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0489. Min Range: -4.0489
Max Act: 4.0489. Min Act: -0.1700
Data Index: 68562 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9551. Min Act: -0.1700
Data Index: 755042 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1010594 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1349246 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1006468 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9238. Min Act: -0.1700
Data Index: 904609 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9238. Min Act: -0.1700
Data Index: 119032 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9707. Min Act: -0.1700
Data Index: 258163 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9082. Min Act: -0.1700
Data Index: 876253 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9238. Min Act: -0.1700
Data Index: 650401 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8925. Min Act: -0.1700
Data Index: 471938 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8925. Min Act: -0.1700
Data Index: 1323487 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9082. Min Act: -0.1700
Data Index: 1050656 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8456. Min Act: -0.1700
Data Index: 1342094 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8143. Min Act: -0.1700
Data Index: 1015684 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8613. Min Act: -0.1700
Data Index: 1216727 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8300. Min Act: -0.1700
Data Index: 93325 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8143. Min Act: -0.1700
Data Index: 805599 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.7518. Min Act: -0.1700
Data Index: 487711 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.7987. Min Act: -0.1700
Data Index: 1128120 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19