Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1963 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1044. Min Range: -3.1044
Max Act: 3.1044. Min Act: -0.1700
Data Index: 189611 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.9465. Min Act: -0.1700
Data Index: 1010068 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.9465. Min Act: -0.1700
Data Index: 1261636 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.9465. Min Act: -0.1700
Data Index: 127939 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.9306. Min Act: -0.1700
Data Index: 543294 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8830. Min Act: -0.1700
Data Index: 41591 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8672. Min Act: -0.1700
Data Index: 896016 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8513. Min Act: -0.1700
Data Index: 351307 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8513. Min Act: -0.1700
Data Index: 1285065 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8672. Min Act: -0.1700
Data Index: 928444 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8513. Min Act: -0.1700
Data Index: 97876 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8513. Min Act: -0.1700
Data Index: 383855 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8036. Min Act: -0.1700
Data Index: 1347901 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.8036. Min Act: -0.1700
Data Index: 330811 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.7876. Min Act: -0.1700
Data Index: 1002298 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.7717. Min Act: -0.1700
Data Index: 679698 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.7717. Min Act: -0.1700
Data Index: 984935 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.7557. Min Act: -0.1700
Data Index: 967479 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.7557. Min Act: -0.1700
Data Index: 484560 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1044. Min Range: -3.1044
Max Act: 2.7557. Min Act: -0.1700
Data Index: 1108015 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19