Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1276 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1804. Min Range: -4.1804
Max Act: 4.1804. Min Act: -0.1700
Data Index: 930377 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1804. Min Range: -4.1804
Max Act: 4.1023. Min Act: -0.1700
Data Index: 152603 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1804. Min Range: -4.1804
Max Act: 4.0710. Min Act: -0.1700
Data Index: 32624 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8834. Min Act: -0.1700
Data Index: 138482 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.9147. Min Act: -0.1700
Data Index: 90812 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8990. Min Act: -0.1699
Data Index: 1056338 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8521. Min Act: -0.1700
Data Index: 239773 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8365. Min Act: -0.1700
Data Index: 770835 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8521. Min Act: -0.1700
Data Index: 1237678 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8521. Min Act: -0.1700
Data Index: 1140070 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8365. Min Act: -0.1700
Data Index: 661245 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7739. Min Act: -0.1700
Data Index: 441419 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8052. Min Act: -0.1700
Data Index: 147661 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7896. Min Act: -0.1700
Data Index: 908155 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.8052. Min Act: -0.1700
Data Index: 1200038 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7583. Min Act: -0.1699
Data Index: 644074 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7583. Min Act: -0.1700
Data Index: 870343 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7426. Min Act: -0.1700
Data Index: 659418 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7739. Min Act: -0.1700
Data Index: 556804 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1804. Min Range: -4.1804
Max Act: 3.7739. Min Act: -0.1700
Data Index: 748297 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19