Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 216 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.8483. Min Act: -0.1700
Data Index: 482303 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.7048. Min Act: -0.1700
Data Index: 479305 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.7208. Min Act: -0.1700
Data Index: 844311 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.7208. Min Act: -0.1700
Data Index: 606416 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.7048. Min Act: -0.1700
Data Index: 509774 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6888. Min Act: -0.1700
Data Index: 1274614 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1104268 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6247. Min Act: -0.1700
Data Index: 677336 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6247. Min Act: -0.1700
Data Index: 56338 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6086. Min Act: -0.1700
Data Index: 834157 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6086. Min Act: -0.1700
Data Index: 491295 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.6086. Min Act: -0.1700
Data Index: 928601 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5925. Min Act: -0.1700
Data Index: 1198038 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5925. Min Act: -0.1700
Data Index: 1277833 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5764. Min Act: -0.1700
Data Index: 257235 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5764. Min Act: -0.1700
Data Index: 4141 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5603. Min Act: -0.1700
Data Index: 234846 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5603. Min Act: -0.1700
Data Index: 4996 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5603. Min Act: -0.1700
Data Index: 749525 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8483. Min Range: -2.8483
Max Act: 2.5603. Min Act: -0.1700
Data Index: 300680 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19