Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 27 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.8739. Min Act: -0.1700
Data Index: 942216 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.8422. Min Act: -0.1700
Data Index: 215192 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.8263. Min Act: -0.1700
Data Index: 1470962 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7785. Min Act: -0.1700
Data Index: 1398734 (Python Code)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7625. Min Act: -0.1700
Data Index: 598046 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7625. Min Act: -0.1700
Data Index: 1402998 (Python Code)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7785. Min Act: -0.1700
Data Index: 1560174 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7306. Min Act: -0.1700
Data Index: 1441254 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7146. Min Act: -0.1700
Data Index: 725048 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.7306. Min Act: -0.1700
Data Index: 1462239 (Python Code)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6986. Min Act: -0.1700
Data Index: 623403 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6986. Min Act: -0.1698
Data Index: 1431461 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6826. Min Act: -0.1700
Data Index: 1619155 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6666. Min Act: -0.1700
Data Index: 1499962 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6826. Min Act: -0.1700
Data Index: 180396 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6666. Min Act: -0.1700
Data Index: 1581798 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6666. Min Act: -0.1700
Data Index: 1635914 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6506. Min Act: -0.1700
Data Index: 1469348 (Python Code)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6506. Min Act: -0.1700
Data Index: 162729 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8739. Min Range: -2.8739
Max Act: 2.6506. Min Act: -0.1700
Data Index: 520462 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19