Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2020 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.2799. Min Act: -0.1700
Data Index: 120769 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.1973. Min Act: -0.1700
Data Index: 446764 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.1307. Min Act: -0.1700
Data Index: 532857 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.1140. Min Act: -0.1700
Data Index: 1202441 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0973. Min Act: -0.1700
Data Index: 65675 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0638. Min Act: -0.1696
Data Index: 1381194 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0973. Min Act: -0.1652
Data Index: 1544330 (Python Code)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0806. Min Act: -0.1700
Data Index: 517651 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0638. Min Act: -0.1681
Data Index: 1104744 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0470. Min Act: -0.1700
Data Index: 42294 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0302. Min Act: -0.1700
Data Index: 1312966 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0638. Min Act: -0.1638
Data Index: 1489389 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0470. Min Act: -0.0833
Data Index: 1574469 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0638. Min Act: -0.1479
Data Index: 1469892 (Python Code)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0302. Min Act: -0.1630
Data Index: 1649248 (Python Code)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0638. Min Act: -0.1700
Data Index: 1073229 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0470. Min Act: -0.1700
Data Index: 546133 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0470. Min Act: -0.1700
Data Index: 202813 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0133. Min Act: -0.1700
Data Index: 888493 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2799. Min Range: -2.2799
Max Act: 2.0133. Min Act: -0.1700
Data Index: 1604967 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19