Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1826 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.3159. Min Act: -0.1697
Data Index: 263489 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2666. Min Act: -0.1699
Data Index: 1117589 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2666. Min Act: -0.1699
Data Index: 1322977 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1699
Data Index: 1500140 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2501. Min Act: -0.1700
Data Index: 907876 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2501. Min Act: -0.1700
Data Index: 633042 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2501. Min Act: -0.1699
Data Index: 1309977 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2501. Min Act: -0.1700
Data Index: 1309594 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1699
Data Index: 1169251 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1699
Data Index: 525419 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1700
Data Index: 828253 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1700
Data Index: 664265 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1700
Data Index: 691158 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1700
Data Index: 885193 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2336. Min Act: -0.1700
Data Index: 1370827 (Python Code)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2170. Min Act: -0.1700
Data Index: 1193418 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2170. Min Act: -0.1663
Data Index: 409540 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2170. Min Act: -0.1694
Data Index: 487797 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2170. Min Act: -0.1699
Data Index: 129482 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2004. Min Act: -0.1700
Data Index: 384098 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19