Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1975 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9780. Min Act: -0.1700
Data Index: 159741 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1271865 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9468. Min Act: -0.1700
Data Index: 317360 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 1284592 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 45189 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1021933 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1016427 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9468. Min Act: -0.1700
Data Index: 1212159 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 1087997 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9468. Min Act: -0.1700
Data Index: 1154914 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 422528 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.8843. Min Act: -0.1700
Data Index: 522458 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.8843. Min Act: -0.1700
Data Index: 216514 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 771085 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 630744 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1262149 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1063515 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 648030 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.9155. Min Act: -0.1700
Data Index: 1013729 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9780. Min Range: -4.9780
Max Act: 4.8843. Min Act: -0.1700
Data Index: 571058 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19