Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1829 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.7199. Min Act: -0.1700
Data Index: 1349324 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.7356. Min Act: -0.1700
Data Index: 1303244 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5793. Min Act: -0.1700
Data Index: 229743 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.6418. Min Act: -0.1700
Data Index: 1324938 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5949. Min Act: -0.1700
Data Index: 9824 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5324. Min Act: -0.1700
Data Index: 269179 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5637. Min Act: -0.1700
Data Index: 901900 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4856. Min Act: -0.1700
Data Index: 263993 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5012. Min Act: -0.1700
Data Index: 336263 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5324. Min Act: -0.1700
Data Index: 1121867 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4699. Min Act: -0.1700
Data Index: 52142 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5012. Min Act: -0.1700
Data Index: 1117340 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4856. Min Act: -0.1700
Data Index: 513515 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5012. Min Act: -0.1700
Data Index: 221382 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4699. Min Act: -0.1700
Data Index: 821705 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4856. Min Act: -0.1700
Data Index: 1315790 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4856. Min Act: -0.1700
Data Index: 365138 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5012. Min Act: -0.1700
Data Index: 649666 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.5012. Min Act: -0.1700
Data Index: 121364 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7356. Min Range: -4.7356
Max Act: 4.4699. Min Act: -0.1700
Data Index: 796718 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19