Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2007 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1539. Min Range: -3.1539
Max Act: 3.1539. Min Act: -0.1700
Data Index: 1008448 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.8057. Min Act: -0.1700
Data Index: 930894 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.7898. Min Act: -0.1700
Data Index: 1256923 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.7100. Min Act: -0.1700
Data Index: 80032 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6940. Min Act: -0.1700
Data Index: 1218334 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6298. Min Act: -0.1700
Data Index: 871318 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6459. Min Act: -0.1700
Data Index: 104037 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6298. Min Act: -0.1700
Data Index: 871989 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6138. Min Act: -0.1700
Data Index: 936688 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6298. Min Act: -0.1700
Data Index: 114283 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.6298. Min Act: -0.1700
Data Index: 621217 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5816. Min Act: -0.1700
Data Index: 629614 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5816. Min Act: -0.1700
Data Index: 1080991 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5655. Min Act: -0.1700
Data Index: 15385 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5493. Min Act: -0.1700
Data Index: 984864 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5493. Min Act: -0.1700
Data Index: 1218392 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5655. Min Act: -0.1700
Data Index: 556643 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5170. Min Act: -0.1700
Data Index: 825654 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5493. Min Act: -0.1700
Data Index: 923564 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1539. Min Range: -3.1539
Max Act: 2.5493. Min Act: -0.1700
Data Index: 16365 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19