Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1834 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5716. Min Act: -0.1700
Data Index: 1217974 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5393. Min Act: -0.1700
Data Index: 686618 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5554. Min Act: -0.1700
Data Index: 1223933 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5231. Min Act: -0.1700
Data Index: 1143204 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5554. Min Act: -0.1700
Data Index: 907019 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5554. Min Act: -0.1700
Data Index: 24282 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5393. Min Act: -0.1700
Data Index: 865564 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5231. Min Act: -0.1700
Data Index: 953125 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.4908. Min Act: -0.1700
Data Index: 512845 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5070. Min Act: -0.1700
Data Index: 290935 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5070. Min Act: -0.1700
Data Index: 227249 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5231. Min Act: -0.1700
Data Index: 518612 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5231. Min Act: -0.1700
Data Index: 426343 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.4908. Min Act: -0.1700
Data Index: 1281395 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.4908. Min Act: -0.1700
Data Index: 830832 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.4908. Min Act: -0.1700
Data Index: 660695 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5070. Min Act: -0.1700
Data Index: 66372 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5070. Min Act: -0.1700
Data Index: 306844 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.5070. Min Act: -0.1700
Data Index: 1001233 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5716. Min Range: -2.5716
Max Act: 2.4908. Min Act: -0.1700
Data Index: 107787 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19