Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 172 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0060. Min Range: -6.0060
Max Act: 6.0060. Min Act: -0.1700
Data Index: 313578 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8497. Min Act: -0.1700
Data Index: 1119104 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8810. Min Act: -0.1700
Data Index: 439384 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.9122. Min Act: -0.1700
Data Index: 381814 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8497. Min Act: -0.1700
Data Index: 802279 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8810. Min Act: -0.1700
Data Index: 1108856 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8497. Min Act: -0.1700
Data Index: 570487 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.9122. Min Act: -0.1700
Data Index: 337426 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8497. Min Act: -0.1700
Data Index: 1299339 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.7872. Min Act: -0.1700
Data Index: 1302931 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.7560. Min Act: -0.1700
Data Index: 260476 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.8185. Min Act: -0.1700
Data Index: 494891 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.6935. Min Act: -0.1700
Data Index: 30232 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.7560. Min Act: -0.1700
Data Index: 76628 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.6935. Min Act: -0.1700
Data Index: 1242418 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.6310. Min Act: -0.1700
Data Index: 908041 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.7247. Min Act: -0.1700
Data Index: 85299 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.7872. Min Act: -0.1700
Data Index: 540984 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.7247. Min Act: -0.1700
Data Index: 1150075 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0060. Min Range: -6.0060
Max Act: 5.6622. Min Act: -0.1700
Data Index: 1130480 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19