Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1453 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.2996. Min Act: -0.1700
Data Index: 637708 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.2996. Min Act: -0.1700
Data Index: 847333 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.2684. Min Act: -0.1700
Data Index: 1274444 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.1746. Min Act: -0.1700
Data Index: 544454 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.2058. Min Act: -0.1700
Data Index: 24925 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.1746. Min Act: -0.1700
Data Index: 1214643 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.1121. Min Act: -0.1700
Data Index: 13650 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.1433. Min Act: -0.1700
Data Index: 1254191 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0808. Min Act: -0.1699
Data Index: 817750 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0808. Min Act: -0.1700
Data Index: 287072 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0808. Min Act: -0.1700
Data Index: 1330680 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.1121. Min Act: -0.1700
Data Index: 669348 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0808. Min Act: -0.1700
Data Index: 325581 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.1121. Min Act: -0.1700
Data Index: 192991 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0495. Min Act: -0.1700
Data Index: 929818 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0495. Min Act: -0.1700
Data Index: 588261 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0808. Min Act: -0.1700
Data Index: 973269 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0495. Min Act: -0.1700
Data Index: 454405 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0183. Min Act: -0.1700
Data Index: 864592 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2996. Min Range: -4.2996
Max Act: 4.0808. Min Act: -0.1700
Data Index: 864238 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19