Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1325 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.8193. Min Act: -0.1700
Data Index: 629046 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.8034. Min Act: -0.1700
Data Index: 1102609 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7715. Min Act: -0.1700
Data Index: 628630 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7874. Min Act: -0.1700
Data Index: 522076 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7715. Min Act: -0.1700
Data Index: 1292973 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7555. Min Act: -0.1700
Data Index: 103031 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7555. Min Act: -0.1700
Data Index: 1195707 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7555. Min Act: -0.1700
Data Index: 944395 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7555. Min Act: -0.1700
Data Index: 819503 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7555. Min Act: -0.1700
Data Index: 939923 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7396. Min Act: -0.1700
Data Index: 1029896 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7236. Min Act: -0.1700
Data Index: 632821 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7236. Min Act: -0.1700
Data Index: 451549 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.7076. Min Act: -0.1700
Data Index: 1156293 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.6916. Min Act: -0.1700
Data Index: 191278 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.6916. Min Act: -0.1700
Data Index: 1046825 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.6596. Min Act: -0.1700
Data Index: 340785 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.6756. Min Act: -0.1700
Data Index: 476984 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.6756. Min Act: -0.1700
Data Index: 180203 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8193. Min Range: -2.8193
Max Act: 2.6596. Min Act: -0.1700
Data Index: 1125359 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19