Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1725 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.4501. Min Act: -0.1700
Data Index: 1169117 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.4501. Min Act: -0.1700
Data Index: 564163 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.3876. Min Act: -0.1700
Data Index: 222422 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.3876. Min Act: -0.1700
Data Index: 863787 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.2626. Min Act: -0.1700
Data Index: 496248 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.2313. Min Act: -0.1700
Data Index: 780063 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.1375. Min Act: -0.1700
Data Index: 1602692 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.1375. Min Act: -0.1700
Data Index: 1547584 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.1375. Min Act: -0.1700
Data Index: 1635451 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0437. Min Act: -0.1700
Data Index: 1392132 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.1063. Min Act: -0.1700
Data Index: 556784 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4501. Min Range: -4.4501
Max Act: 3.9812. Min Act: -0.1700
Data Index: 27621 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0437. Min Act: -0.1700
Data Index: 141410 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0437. Min Act: -0.1700
Data Index: 1424905 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0437. Min Act: -0.1700
Data Index: 643255 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0125. Min Act: -0.1700
Data Index: 52702 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0437. Min Act: -0.1700
Data Index: 217701 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0125. Min Act: -0.1700
Data Index: 974958 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4501. Min Range: -4.4501
Max Act: 3.9499. Min Act: -0.1700
Data Index: 671107 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4501. Min Range: -4.4501
Max Act: 4.0125. Min Act: -0.1700
Data Index: 1103788 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19