Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1549 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.4520. Min Act: -0.1700
Data Index: 872907 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.4520. Min Act: -0.1700
Data Index: 225978 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.4358. Min Act: -0.1700
Data Index: 216576 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.4032. Min Act: -0.1700
Data Index: 613330 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3869. Min Act: -0.1700
Data Index: 1158288 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3869. Min Act: -0.1700
Data Index: 1118163 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3705. Min Act: -0.1700
Data Index: 687184 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3705. Min Act: -0.1700
Data Index: 371269 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3869. Min Act: -0.1700
Data Index: 163075 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3869. Min Act: -0.1700
Data Index: 107232 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3542. Min Act: -0.1700
Data Index: 128070 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3378. Min Act: -0.1700
Data Index: 371073 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3214. Min Act: -0.1700
Data Index: 965293 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3378. Min Act: -0.1700
Data Index: 600587 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3378. Min Act: -0.1700
Data Index: 984313 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3542. Min Act: -0.1700
Data Index: 825861 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3378. Min Act: -0.1700
Data Index: 285828 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3378. Min Act: -0.1700
Data Index: 526304 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3214. Min Act: -0.1700
Data Index: 1052206 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4520. Min Range: -2.4520
Max Act: 2.3214. Min Act: -0.1700
Data Index: 1170366 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19