Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 175 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.5009. Min Act: -0.1700
Data Index: 962926 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.3052. Min Act: -0.1700
Data Index: 716534 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.3052. Min Act: -0.1700
Data Index: 650115 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.3216. Min Act: -0.1700
Data Index: 385696 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2887. Min Act: -0.1700
Data Index: 865732 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2887. Min Act: -0.1700
Data Index: 328829 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2887. Min Act: -0.1700
Data Index: 1149259 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2722. Min Act: -0.1700
Data Index: 671663 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2887. Min Act: -0.1700
Data Index: 655282 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2558. Min Act: -0.1700
Data Index: 638837 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2887. Min Act: -0.1700
Data Index: 877315 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2887. Min Act: -0.1700
Data Index: 1308336 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2558. Min Act: -0.1700
Data Index: 204530 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2558. Min Act: -0.1700
Data Index: 182975 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2558. Min Act: -0.1700
Data Index: 577263 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2392. Min Act: -0.1700
Data Index: 129788 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2392. Min Act: -0.1700
Data Index: 331140 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2392. Min Act: -0.1700
Data Index: 942131 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2558. Min Act: -0.1700
Data Index: 652934 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5009. Min Range: -2.5009
Max Act: 2.2392. Min Act: -0.1700
Data Index: 761673 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19