Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1187 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.4107. Min Act: -0.1700
Data Index: 738529 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.4107. Min Act: -0.1699
Data Index: 1066906 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.3482. Min Act: -0.1700
Data Index: 1370218 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0982. Min Act: -0.1700
Data Index: 872293 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.2232. Min Act: -0.1700
Data Index: 625142 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.1294. Min Act: -0.1700
Data Index: 311780 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.1294. Min Act: -0.1700
Data Index: 383769 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0982. Min Act: -0.1700
Data Index: 796654 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0669. Min Act: -0.1700
Data Index: 1258954 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0044. Min Act: -0.1700
Data Index: 1016145 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0669. Min Act: -0.1700
Data Index: 1347462 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0356. Min Act: -0.1700
Data Index: 491325 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4107. Min Range: -4.4107
Max Act: 3.9731. Min Act: -0.1700
Data Index: 1248399 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0044. Min Act: -0.1700
Data Index: 1208693 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0044. Min Act: -0.1700
Data Index: 247701 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4107. Min Range: -4.4107
Max Act: 3.9418. Min Act: -0.1700
Data Index: 1039032 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4107. Min Range: -4.4107
Max Act: 3.9731. Min Act: -0.1700
Data Index: 1082639 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4107. Min Range: -4.4107
Max Act: 3.9106. Min Act: -0.1700
Data Index: 750499 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4107. Min Range: -4.4107
Max Act: 3.9731. Min Act: -0.1700
Data Index: 381922 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4107. Min Range: -4.4107
Max Act: 4.0356. Min Act: -0.1700
Data Index: 490333 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19