Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1776 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.3277. Min Act: -0.1700
Data Index: 544004 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.2784. Min Act: -0.1700
Data Index: 1034782 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.2288. Min Act: -0.1700
Data Index: 393590 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.2123. Min Act: -0.1700
Data Index: 368786 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1957. Min Act: -0.1700
Data Index: 331284 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1625. Min Act: -0.1700
Data Index: 289755 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1791. Min Act: -0.1700
Data Index: 129122 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1791. Min Act: -0.1700
Data Index: 335998 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1791. Min Act: -0.1700
Data Index: 622393 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1625. Min Act: -0.1700
Data Index: 1339154 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1458. Min Act: -0.1700
Data Index: 1247571 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1292. Min Act: -0.1700
Data Index: 578476 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1125. Min Act: -0.1700
Data Index: 976823 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1125. Min Act: -0.1700
Data Index: 1358437 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1125. Min Act: -0.1700
Data Index: 38037 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.0957. Min Act: -0.1700
Data Index: 1620602 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.0790. Min Act: -0.1700
Data Index: 216477 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.0957. Min Act: -0.1700
Data Index: 823347 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.0957. Min Act: -0.1700
Data Index: 1261844 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3277. Min Range: -2.3277
Max Act: 2.1125. Min Act: -0.1700
Data Index: 1023492 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19