Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1772 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.9439. Min Act: -0.1700
Data Index: 1320688 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8805. Min Act: -0.1700
Data Index: 286584 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8646. Min Act: -0.1700
Data Index: 1032378 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8805. Min Act: -0.1700
Data Index: 254470 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8487. Min Act: -0.1700
Data Index: 1453010 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8646. Min Act: -0.1700
Data Index: 343414 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8646. Min Act: -0.1700
Data Index: 174810 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8487. Min Act: -0.1700
Data Index: 958942 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8487. Min Act: -0.1700
Data Index: 838377 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8646. Min Act: -0.1700
Data Index: 1027679 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8328. Min Act: -0.1700
Data Index: 621632 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8487. Min Act: -0.1700
Data Index: 631551 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8487. Min Act: -0.1700
Data Index: 212603 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8169. Min Act: -0.1700
Data Index: 812622 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8487. Min Act: -0.1700
Data Index: 1154451 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8328. Min Act: -0.1700
Data Index: 548876 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8169. Min Act: -0.1700
Data Index: 1089863 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8169. Min Act: -0.1700
Data Index: 840238 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8169. Min Act: -0.1700
Data Index: 845951 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9439. Min Range: -2.9439
Max Act: 2.8169. Min Act: -0.1700
Data Index: 873938 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19