Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1553 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.9863. Min Act: -0.1700
Data Index: 890542 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.7363. Min Act: -0.1700
Data Index: 363441 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.6582. Min Act: -0.1700
Data Index: 517105 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.5175. Min Act: -0.1700
Data Index: 1354669 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4863. Min Act: -0.1700
Data Index: 368332 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4550. Min Act: -0.1700
Data Index: 685802 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4863. Min Act: -0.1700
Data Index: 1236015 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.3769. Min Act: -0.1700
Data Index: 431925 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.3925. Min Act: -0.1700
Data Index: 368617 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4863. Min Act: -0.1700
Data Index: 400513 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4394. Min Act: -0.1700
Data Index: 325971 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4081. Min Act: -0.1700
Data Index: 253877 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4081. Min Act: -0.1700
Data Index: 320838 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4394. Min Act: -0.1700
Data Index: 76310 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4394. Min Act: -0.1700
Data Index: 1229802 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.3925. Min Act: -0.1700
Data Index: 998258 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.3769. Min Act: -0.1700
Data Index: 926566 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.4394. Min Act: -0.1700
Data Index: 526762 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.2519. Min Act: -0.1700
Data Index: 1559320 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9863. Min Range: -4.9863
Max Act: 4.3769. Min Act: -0.1700
Data Index: 148493 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19