Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1844 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.2703. Min Act: -0.1700
Data Index: 235907 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.2373. Min Act: -0.1700
Data Index: 778448 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.2208. Min Act: -0.1700
Data Index: 157721 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1876. Min Act: -0.1700
Data Index: 111266 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.2042. Min Act: -0.1700
Data Index: 235782 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1876. Min Act: -0.1700
Data Index: 815934 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.2042. Min Act: -0.1700
Data Index: 402255 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1710. Min Act: -0.1700
Data Index: 1018618 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 43790 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1710. Min Act: -0.1700
Data Index: 1082015 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1876. Min Act: -0.1700
Data Index: 731287 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1377. Min Act: -0.1700
Data Index: 244185 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 166355 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 948012 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 799654 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 661782 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 1199067 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1544. Min Act: -0.1700
Data Index: 61476 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1210. Min Act: -0.1700
Data Index: 745050 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2703. Min Range: -2.2703
Max Act: 2.1377. Min Act: -0.1700
Data Index: 756271 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19