Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 889 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.5109. Min Act: -0.1700
Data Index: 885880 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.2921. Min Act: -0.1700
Data Index: 140978 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.2921. Min Act: -0.1700
Data Index: 769555 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.2296. Min Act: -0.1700
Data Index: 718410 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.2296. Min Act: -0.1700
Data Index: 1268821 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1983. Min Act: -0.1700
Data Index: 77810 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1983. Min Act: -0.1700
Data Index: 396110 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1983. Min Act: -0.1700
Data Index: 1159609 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1983. Min Act: -0.1700
Data Index: 317454 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1358. Min Act: -0.1700
Data Index: 1008122 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1358. Min Act: -0.1700
Data Index: 492267 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1671. Min Act: -0.1700
Data Index: 1215960 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.0733. Min Act: -0.1700
Data Index: 976573 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1045. Min Act: -0.1700
Data Index: 1124891 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1045. Min Act: -0.1700
Data Index: 1005543 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1358. Min Act: -0.1700
Data Index: 746081 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1045. Min Act: -0.1700
Data Index: 314656 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.1045. Min Act: -0.1700
Data Index: 1183496 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.0420. Min Act: -0.1700
Data Index: 228317 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5109. Min Range: -4.5109
Max Act: 4.0733. Min Act: -0.1700
Data Index: 441973 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19