Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1784 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.4417. Min Act: -0.1700
Data Index: 1409000 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.2742. Min Act: -0.1700
Data Index: 790419 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.2125. Min Act: -0.1700
Data Index: 959254 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1773. Min Act: -0.1691
Data Index: 420170 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1773. Min Act: -0.1700
Data Index: 1296446 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1773. Min Act: -0.1677
Data Index: 1161283 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1685. Min Act: -0.1700
Data Index: 266569 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1685. Min Act: -0.1621
Data Index: 844370 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 88339 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1685. Min Act: -0.1700
Data Index: 754730 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 1654722 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1509. Min Act: -0.1700
Data Index: 1488442 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 1627797 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1509. Min Act: -0.1700
Data Index: 985788 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 154863 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1592
Data Index: 561096 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 353420 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 449896 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1597. Min Act: -0.1700
Data Index: 1161134 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4417. Min Range: -1.4417
Max Act: 1.1509. Min Act: -0.1700
Data Index: 155310 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19