Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 320 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.9632. Min Act: -0.1700
Data Index: 386477 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.9293. Min Act: -0.1700
Data Index: 777417 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.8526. Min Act: -0.1700
Data Index: 672856 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.8354. Min Act: -0.1700
Data Index: 953715 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.8354. Min Act: -0.1700
Data Index: 1338888 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.8269. Min Act: -0.1700
Data Index: 415153 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.8183. Min Act: -0.1700
Data Index: 387153 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.8011. Min Act: -0.1700
Data Index: 1027763 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7925. Min Act: -0.1700
Data Index: 666351 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7925. Min Act: -0.1700
Data Index: 1349208 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7925. Min Act: -0.1700
Data Index: 718483 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7753. Min Act: -0.1700
Data Index: 877949 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7839. Min Act: -0.1700
Data Index: 487040 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7839. Min Act: -0.1700
Data Index: 1201845 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7925. Min Act: -0.1700
Data Index: 191070 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7667. Min Act: -0.1700
Data Index: 946015 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7494. Min Act: -0.1700
Data Index: 1245793 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7494. Min Act: -0.1700
Data Index: 821838 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7494. Min Act: -0.1700
Data Index: 1022815 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9632. Min Range: -1.9632
Max Act: 1.7494. Min Act: -0.1700
Data Index: 127487 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19