Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.6042. Min Act: -0.1700
Data Index: 870306 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.5074. Min Act: -0.1700
Data Index: 818268 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4912. Min Act: -0.1700
Data Index: 1275177 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4912. Min Act: -0.1700
Data Index: 583136 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4588. Min Act: -0.1700
Data Index: 1131646 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4425. Min Act: -0.1700
Data Index: 795253 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4588. Min Act: -0.1700
Data Index: 482020 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4588. Min Act: -0.1700
Data Index: 601238 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4425. Min Act: -0.1700
Data Index: 109929 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 659980 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4425. Min Act: -0.1700
Data Index: 467828 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 1261683 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4425. Min Act: -0.1700
Data Index: 943953 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 800874 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 429129 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 725822 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 1232829 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 1287072 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4262. Min Act: -0.1700
Data Index: 1170375 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6042. Min Range: -2.6042
Max Act: 2.4100. Min Act: -0.1700
Data Index: 659820 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19