Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 840 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.2529. Min Act: -0.1700
Data Index: 313010 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.0653. Min Act: -0.1700
Data Index: 1039084 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.0028. Min Act: -0.1700
Data Index: 498529 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9872. Min Act: -0.1700
Data Index: 464045 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.0028. Min Act: -0.1700
Data Index: 398091 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9872. Min Act: -0.1700
Data Index: 866401 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.0184. Min Act: -0.1700
Data Index: 255702 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.0028. Min Act: -0.1700
Data Index: 421668 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2529. Min Range: -4.2529
Max Act: 4.0028. Min Act: -0.1700
Data Index: 618656 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9715. Min Act: -0.1700
Data Index: 1076958 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9559. Min Act: -0.1700
Data Index: 176885 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9872. Min Act: -0.1700
Data Index: 1342877 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9559. Min Act: -0.1700
Data Index: 898523 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9246. Min Act: -0.1700
Data Index: 763652 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9403. Min Act: -0.1700
Data Index: 755657 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9559. Min Act: -0.1700
Data Index: 93794 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9090. Min Act: -0.1700
Data Index: 1297020 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9559. Min Act: -0.1700
Data Index: 1006224 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9090. Min Act: -0.1700
Data Index: 494586 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2529. Min Range: -4.2529
Max Act: 3.9246. Min Act: -0.1700
Data Index: 677618 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19