Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 186 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.4809. Min Act: -0.1700
Data Index: 1079118 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3669. Min Act: -0.1700
Data Index: 1174634 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3669. Min Act: -0.1700
Data Index: 347499 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3832. Min Act: -0.1700
Data Index: 360340 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3669. Min Act: -0.1700
Data Index: 575473 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3669. Min Act: -0.1700
Data Index: 479940 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3341. Min Act: -0.1700
Data Index: 927001 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3669. Min Act: -0.1700
Data Index: 751771 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3505. Min Act: -0.1700
Data Index: 308555 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3505. Min Act: -0.1700
Data Index: 630109 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3505. Min Act: -0.1700
Data Index: 642326 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3177. Min Act: -0.1700
Data Index: 61840 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3341. Min Act: -0.1700
Data Index: 910712 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3341. Min Act: -0.1700
Data Index: 943952 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3341. Min Act: -0.1700
Data Index: 564763 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3341. Min Act: -0.1700
Data Index: 582839 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3177. Min Act: -0.1700
Data Index: 963797 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3341. Min Act: -0.1700
Data Index: 1099977 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3505. Min Act: -0.1700
Data Index: 252180 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4809. Min Range: -2.4809
Max Act: 2.3177. Min Act: -0.1700
Data Index: 61716 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19