Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 502 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2853. Min Act: -0.1700
Data Index: 1196717 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2853. Min Act: -0.1700
Data Index: 1314685 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2688. Min Act: -0.1700
Data Index: 1219994 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2688. Min Act: -0.1700
Data Index: 533639 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2523. Min Act: -0.1700
Data Index: 609304 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2358. Min Act: -0.1700
Data Index: 1252090 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2523. Min Act: -0.1700
Data Index: 337046 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2523. Min Act: -0.1700
Data Index: 869596 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2358. Min Act: -0.1700
Data Index: 261510 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2358. Min Act: -0.1700
Data Index: 472686 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2192. Min Act: -0.1700
Data Index: 1310096 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2192. Min Act: -0.1700
Data Index: 748551 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2192. Min Act: -0.1700
Data Index: 295220 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.2027. Min Act: -0.1700
Data Index: 175488 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.1528. Min Act: -0.1700
Data Index: 30055 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.1861. Min Act: -0.1700
Data Index: 1197281 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.1695. Min Act: -0.1700
Data Index: 292789 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.1861. Min Act: -0.1700
Data Index: 901630 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.1528. Min Act: -0.1700
Data Index: 441719 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2853. Min Range: -2.2853
Max Act: 2.1528. Min Act: -0.1700
Data Index: 847717 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19