Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 326 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.2025. Min Act: -0.1700
Data Index: 1145443 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.2025. Min Act: -0.1700
Data Index: 264599 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.1711. Min Act: -0.1700
Data Index: 561676 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.1238. Min Act: -0.1700
Data Index: 1145094 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.0923. Min Act: -0.1700
Data Index: 702638 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.0765. Min Act: -0.1700
Data Index: 520223 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.0449. Min Act: -0.1700
Data Index: 417752 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.0291. Min Act: -0.1700
Data Index: 83672 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9817. Min Act: -0.1700
Data Index: 1129906 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9975. Min Act: -0.1700
Data Index: 385736 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9975. Min Act: -0.1700
Data Index: 500461 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9817. Min Act: -0.1700
Data Index: 909321 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2025. Min Range: -3.2025
Max Act: 3.0291. Min Act: -0.1700
Data Index: 429013 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9975. Min Act: -0.1700
Data Index: 526161 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9659. Min Act: -0.1700
Data Index: 1094686 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9817. Min Act: -0.1700
Data Index: 866852 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9817. Min Act: -0.1700
Data Index: 921353 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9501. Min Act: -0.1700
Data Index: 411379 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9975. Min Act: -0.1700
Data Index: 8209 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2025. Min Range: -3.2025
Max Act: 2.9501. Min Act: -0.1700
Data Index: 862350 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19