Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 52 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.9834. Min Act: -0.1700
Data Index: 282067 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.9042. Min Act: -0.1700
Data Index: 304836 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8883. Min Act: -0.1700
Data Index: 1278240 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.9042. Min Act: -0.1700
Data Index: 896119 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.9042. Min Act: -0.1700
Data Index: 557495 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8566. Min Act: -0.1700
Data Index: 789488 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8725. Min Act: -0.1700
Data Index: 30157 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8725. Min Act: -0.1700
Data Index: 1031141 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8566. Min Act: -0.1700
Data Index: 547177 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8566. Min Act: -0.1700
Data Index: 130563 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8566. Min Act: -0.1700
Data Index: 97784 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8566. Min Act: -0.1700
Data Index: 268626 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1302096 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8248. Min Act: -0.1700
Data Index: 97152 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8248. Min Act: -0.1700
Data Index: 899659 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8407. Min Act: -0.1700
Data Index: 52920 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8248. Min Act: -0.1700
Data Index: 886680 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8407. Min Act: -0.1700
Data Index: 1340785 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8407. Min Act: -0.1700
Data Index: 1016833 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9834. Min Range: -2.9834
Max Act: 2.8248. Min Act: -0.1700
Data Index: 203055 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19