Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1609 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.9774. Min Act: -0.1700
Data Index: 821799 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.9299. Min Act: -0.1700
Data Index: 185663 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8982. Min Act: -0.1700
Data Index: 232773 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.9141. Min Act: -0.1700
Data Index: 542971 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8823. Min Act: -0.1700
Data Index: 829030 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8982. Min Act: -0.1700
Data Index: 1027685 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8982. Min Act: -0.1700
Data Index: 228361 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 70972 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8823. Min Act: -0.1700
Data Index: 1032533 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8823. Min Act: -0.1700
Data Index: 437558 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8823. Min Act: -0.1700
Data Index: 1063414 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 1087476 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 1138927 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 773220 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8506. Min Act: -0.1700
Data Index: 1583376 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8506. Min Act: -0.1700
Data Index: 145171 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 624426 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 1084314 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8665. Min Act: -0.1700
Data Index: 243579 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9774. Min Range: -2.9774
Max Act: 2.8506. Min Act: -0.1700
Data Index: 219810 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19