Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1950 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.3019. Min Act: -0.1700
Data Index: 689515 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.1696. Min Act: -0.1700
Data Index: 757311 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.1530. Min Act: -0.1700
Data Index: 1222591 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.1696. Min Act: -0.1700
Data Index: 907378 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.1363. Min Act: -0.1700
Data Index: 1335145 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.1197. Min Act: -0.1700
Data Index: 170405 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0862. Min Act: -0.1700
Data Index: 1184161 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0862. Min Act: -0.1700
Data Index: 383133 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.1029. Min Act: -0.1700
Data Index: 1244239 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0694. Min Act: -0.1700
Data Index: 166208 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0694. Min Act: -0.1700
Data Index: 197109 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0694. Min Act: -0.1700
Data Index: 902991 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0694. Min Act: -0.1700
Data Index: 691682 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0862. Min Act: -0.1700
Data Index: 548494 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0862. Min Act: -0.1700
Data Index: 411459 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0694. Min Act: -0.1700
Data Index: 1340747 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0694. Min Act: -0.1700
Data Index: 945377 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0526. Min Act: -0.1700
Data Index: 674740 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0526. Min Act: -0.1700
Data Index: 518841 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3019. Min Range: -2.3019
Max Act: 2.0526. Min Act: -0.1700
Data Index: 1202364 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19