Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 285 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.2498. Min Act: -0.1700
Data Index: 1272251 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.2811. Min Act: -0.1700
Data Index: 820038 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.1873. Min Act: -0.1700
Data Index: 253666 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.1248. Min Act: -0.1700
Data Index: 939075 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0935. Min Act: -0.1700
Data Index: 337406 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0623. Min Act: -0.1700
Data Index: 421167 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 1055587 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0935. Min Act: -0.1700
Data Index: 249733 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 1465176 (Python Code)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 872463 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 91000 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2811. Min Range: -4.2811
Max Act: 3.9997. Min Act: -0.1700
Data Index: 216756 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2811. Min Range: -4.2811
Max Act: 3.9997. Min Act: -0.1700
Data Index: 574321 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 1215491 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 659534 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 240358 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2811. Min Range: -4.2811
Max Act: 3.9685. Min Act: -0.1700
Data Index: 256608 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2811. Min Range: -4.2811
Max Act: 3.9997. Min Act: -0.1700
Data Index: 654701 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2811. Min Range: -4.2811
Max Act: 4.0310. Min Act: -0.1700
Data Index: 828527 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2811. Min Range: -4.2811
Max Act: 3.9685. Min Act: -0.1700
Data Index: 919548 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19