Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1953 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.4857. Min Act: -0.1700
Data Index: 760352 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.4857. Min Act: -0.1700
Data Index: 198703 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.2669. Min Act: -0.1700
Data Index: 403862 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.2357. Min Act: -0.1700
Data Index: 1227792 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.2044. Min Act: -0.1700
Data Index: 359763 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.2044. Min Act: -0.1700
Data Index: 1246317 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.2044. Min Act: -0.1700
Data Index: 144399 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.1419. Min Act: -0.1700
Data Index: 237372 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.1107. Min Act: -0.1700
Data Index: 355943 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.1419. Min Act: -0.1700
Data Index: 312541 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.1732. Min Act: -0.1700
Data Index: 401256 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.1107. Min Act: -0.1700
Data Index: 756098 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.1107. Min Act: -0.1700
Data Index: 665420 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0794. Min Act: -0.1700
Data Index: 553548 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0794. Min Act: -0.1700
Data Index: 1108347 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0482. Min Act: -0.1700
Data Index: 786260 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0794. Min Act: -0.1700
Data Index: 1254511 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0794. Min Act: -0.1700
Data Index: 782138 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0794. Min Act: -0.1700
Data Index: 22034 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4857. Min Range: -6.4857
Max Act: 6.0794. Min Act: -0.1700
Data Index: 969940 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19