Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1115 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.8184. Min Act: -0.1700
Data Index: 1198223 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.7559. Min Act: -0.1700
Data Index: 317639 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.7559. Min Act: -0.1700
Data Index: 974269 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.7559. Min Act: -0.1700
Data Index: 654910 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.7559. Min Act: -0.1700
Data Index: 541549 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6621. Min Act: -0.1699
Data Index: 593400 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6934. Min Act: -0.1700
Data Index: 857010 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6309. Min Act: -0.1700
Data Index: 286969 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6621. Min Act: -0.1700
Data Index: 257886 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6621. Min Act: -0.1700
Data Index: 1265727 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6309. Min Act: -0.1700
Data Index: 510976 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6621. Min Act: -0.1700
Data Index: 727779 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6621. Min Act: -0.1700
Data Index: 361730 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6934. Min Act: -0.1700
Data Index: 141268 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.5996. Min Act: -0.1700
Data Index: 656862 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.5684. Min Act: -0.1700
Data Index: 114138 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.5371. Min Act: -0.1700
Data Index: 1118512 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.6309. Min Act: -0.1700
Data Index: 822509 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.5996. Min Act: -0.1700
Data Index: 594058 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8184. Min Range: -4.8184
Max Act: 4.5996. Min Act: -0.1700
Data Index: 459901 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19