Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 63 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.9197. Min Act: -0.1700
Data Index: 750509 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.6385. Min Act: -0.1700
Data Index: 50784 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3885. Min Act: -0.1700
Data Index: 1177446 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4510. Min Act: -0.1700
Data Index: 384981 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3572. Min Act: -0.1700
Data Index: 915798 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.4197. Min Act: -0.1700
Data Index: 913223 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3885. Min Act: -0.1700
Data Index: 1310720 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3572. Min Act: -0.1700
Data Index: 1211884 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3572. Min Act: -0.1700
Data Index: 45169 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2322. Min Act: -0.1700
Data Index: 1292469 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3260. Min Act: -0.1700
Data Index: 1311663 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2947. Min Act: -0.1700
Data Index: 1017292 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2322. Min Act: -0.1700
Data Index: 575457 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2322. Min Act: -0.1700
Data Index: 513959 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2635. Min Act: -0.1700
Data Index: 84394 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.3260. Min Act: -0.1700
Data Index: 464099 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2322. Min Act: -0.1700
Data Index: 135799 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2010. Min Act: -0.1700
Data Index: 878572 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2010. Min Act: -0.1700
Data Index: 1193188 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9197. Min Range: -6.9197
Max Act: 6.2322. Min Act: -0.1700
Data Index: 758844 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19