Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1395 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.9731. Min Act: -0.1700
Data Index: 1145375 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.8481. Min Act: -0.1700
Data Index: 1130289 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.9106. Min Act: -0.1699
Data Index: 1305738 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.8481. Min Act: -0.1699
Data Index: 851723 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.8481. Min Act: -0.1700
Data Index: 911898 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.7856. Min Act: -0.1700
Data Index: 1040027 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.7231. Min Act: -0.1700
Data Index: 637840 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.7231. Min Act: -0.1700
Data Index: 1076721 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.7231. Min Act: -0.1700
Data Index: 604202 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5981. Min Act: -0.1699
Data Index: 322212 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.6606. Min Act: -0.1700
Data Index: 163330 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5981. Min Act: -0.1700
Data Index: 2749 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5981. Min Act: -0.1700
Data Index: 1546193 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5356. Min Act: -0.1700
Data Index: 862494 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5356. Min Act: -0.1700
Data Index: 349300 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5356. Min Act: -0.1699
Data Index: 1072762 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.5356. Min Act: -0.1700
Data Index: 1304941 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.4731. Min Act: -0.1700
Data Index: 1507326 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.4106. Min Act: -0.1700
Data Index: 986659 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9731. Min Range: -6.9731
Max Act: 6.4731. Min Act: -0.1700
Data Index: 141536 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19