Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 691 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.8499. Min Act: -0.1700
Data Index: 468744 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.8187. Min Act: -0.1700
Data Index: 596789 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.7874. Min Act: -0.1700
Data Index: 1286604 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.7874. Min Act: -0.1700
Data Index: 1085734 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.6936. Min Act: -0.1700
Data Index: 386030 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.6624. Min Act: -0.1700
Data Index: 1194970 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.6624. Min Act: -0.1700
Data Index: 761228 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5999. Min Act: -0.1700
Data Index: 274193 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.6311. Min Act: -0.1700
Data Index: 236019 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5686. Min Act: -0.1700
Data Index: 954567 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5686. Min Act: -0.1700
Data Index: 1021597 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5061. Min Act: -0.1700
Data Index: 196466 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.4749. Min Act: -0.1700
Data Index: 45454 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5061. Min Act: -0.1700
Data Index: 954317 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.4436. Min Act: -0.1700
Data Index: 1356582 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5686. Min Act: -0.1700
Data Index: 1202266 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.4749. Min Act: -0.1700
Data Index: 1049055 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5061. Min Act: -0.1700
Data Index: 866726 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.5061. Min Act: -0.1700
Data Index: 1301039 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8499. Min Range: -4.8499
Max Act: 4.4436. Min Act: -0.1700
Data Index: 217382 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19