Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2009 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1287. Min Range: -3.1287
Max Act: 3.1287. Min Act: -0.1700
Data Index: 599188 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.7803. Min Act: -0.1700
Data Index: 422061 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.7483. Min Act: -0.1700
Data Index: 1197948 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.7483. Min Act: -0.1700
Data Index: 1022457 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.7164. Min Act: -0.1700
Data Index: 560673 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.7164. Min Act: -0.1700
Data Index: 1029250 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.7004. Min Act: -0.1700
Data Index: 567947 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6523. Min Act: -0.1700
Data Index: 1359724 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6363. Min Act: -0.1700
Data Index: 624254 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6041. Min Act: -0.1700
Data Index: 1155535 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6202. Min Act: -0.1700
Data Index: 623591 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6202. Min Act: -0.1700
Data Index: 150605 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.5880. Min Act: -0.1700
Data Index: 1281302 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6041. Min Act: -0.1700
Data Index: 40058 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.6041. Min Act: -0.1700
Data Index: 856795 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.5880. Min Act: -0.1700
Data Index: 861155 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.5880. Min Act: -0.1700
Data Index: 807784 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.5719. Min Act: -0.1700
Data Index: 513754 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.5719. Min Act: -0.1700
Data Index: 158063 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1287. Min Range: -3.1287
Max Act: 2.5719. Min Act: -0.1700
Data Index: 65485 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19