Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 24 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.5180. Min Range: -6.5180
Max Act: 6.5180. Min Act: -0.1699
Data Index: 1192467 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5180. Min Range: -6.5180
Max Act: 6.3617. Min Act: -0.1700
Data Index: 758960 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5180. Min Range: -6.5180
Max Act: 6.0805. Min Act: -0.1700
Data Index: 1110840 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.8305. Min Act: -0.1700
Data Index: 178142 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7367. Min Act: -0.1700
Data Index: 1355298 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7992. Min Act: -0.1700
Data Index: 1291021 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7680. Min Act: -0.1700
Data Index: 397561 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7680. Min Act: -0.1700
Data Index: 28231 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 113539 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 1309743 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7680. Min Act: -0.1700
Data Index: 800800 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.7055. Min Act: -0.1700
Data Index: 172846 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6430. Min Act: -0.1700
Data Index: 607005 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6117. Min Act: -0.1700
Data Index: 211984 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6742. Min Act: -0.1700
Data Index: 1227030 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6742. Min Act: -0.1700
Data Index: 339471 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6430. Min Act: -0.1700
Data Index: 697637 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6742. Min Act: -0.1700
Data Index: 894577 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6430. Min Act: -0.1700
Data Index: 261995 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5180. Min Range: -6.5180
Max Act: 5.6430. Min Act: -0.1700
Data Index: 461862 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19