Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 95 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0771. Min Range: -3.0771
Max Act: 3.0771. Min Act: -0.1700
Data Index: 25362 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9823. Min Act: -0.1700
Data Index: 297184 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9823. Min Act: -0.1700
Data Index: 1331734 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9665. Min Act: -0.1700
Data Index: 879491 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9665. Min Act: -0.1700
Data Index: 554883 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9506. Min Act: -0.1700
Data Index: 1148498 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9506. Min Act: -0.1700
Data Index: 1307851 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9348. Min Act: -0.1700
Data Index: 521038 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9190. Min Act: -0.1700
Data Index: 677456 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9190. Min Act: -0.1700
Data Index: 754031 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9348. Min Act: -0.1700
Data Index: 764524 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9190. Min Act: -0.1700
Data Index: 934900 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9190. Min Act: -0.1700
Data Index: 668420 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.8714. Min Act: -0.1700
Data Index: 425158 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9031. Min Act: -0.1700
Data Index: 1209752 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9031. Min Act: -0.1700
Data Index: 889430 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9031. Min Act: -0.1700
Data Index: 1146085 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.8872. Min Act: -0.1700
Data Index: 1182827 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9190. Min Act: -0.1700
Data Index: 795630 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0771. Min Range: -3.0771
Max Act: 2.9031. Min Act: -0.1700
Data Index: 472006 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19