Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1983 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0484. Min Range: -4.0484
Max Act: 4.0484. Min Act: -0.1700
Data Index: 474425 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.9546. Min Act: -0.1700
Data Index: 914037 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.8921. Min Act: -0.1700
Data Index: 93916 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7982. Min Act: -0.1700
Data Index: 118779 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7982. Min Act: -0.1700
Data Index: 830432 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7670. Min Act: -0.1700
Data Index: 1342665 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7357. Min Act: -0.1700
Data Index: 846710 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7670. Min Act: -0.1700
Data Index: 994066 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7670. Min Act: -0.1700
Data Index: 505572 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7044. Min Act: -0.1700
Data Index: 425974 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7670. Min Act: -0.1700
Data Index: 450085 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7357. Min Act: -0.1700
Data Index: 105852 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7670. Min Act: -0.1700
Data Index: 445812 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7044. Min Act: -0.1700
Data Index: 785933 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7044. Min Act: -0.1700
Data Index: 380349 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7044. Min Act: -0.1700
Data Index: 761149 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.6731. Min Act: -0.1700
Data Index: 1063334 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.6731. Min Act: -0.1700
Data Index: 1051955 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7357. Min Act: -0.1700
Data Index: 520595 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0484. Min Range: -4.0484
Max Act: 3.7044. Min Act: -0.1700
Data Index: 884885 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19