Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1525 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.9897. Min Act: -0.1700
Data Index: 822546 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.9897. Min Act: -0.1700
Data Index: 850715 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8960. Min Act: -0.1700
Data Index: 226985 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.9897. Min Act: -0.1700
Data Index: 139839 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.9585. Min Act: -0.1700
Data Index: 783090 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.9585. Min Act: -0.1700
Data Index: 1089940 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.9272. Min Act: -0.1700
Data Index: 386672 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 1049471 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 635222 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8960. Min Act: -0.1700
Data Index: 357767 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8335. Min Act: -0.1700
Data Index: 1241981 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 994817 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 506871 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8335. Min Act: -0.1700
Data Index: 378361 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8960. Min Act: -0.1700
Data Index: 248337 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8022. Min Act: -0.1700
Data Index: 267810 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1222906 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 163577 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 364989 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9897. Min Range: -4.9897
Max Act: 4.8647. Min Act: -0.1700
Data Index: 1158537 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19