Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2028 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.3809. Min Act: -0.1700
Data Index: 1120073 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.3184. Min Act: -0.1700
Data Index: 1118701 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.2871. Min Act: -0.1700
Data Index: 1298340 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.2871. Min Act: -0.1700
Data Index: 1339886 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.2246. Min Act: -0.1700
Data Index: 948365 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1934. Min Act: -0.1700
Data Index: 1303850 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1934. Min Act: -0.1700
Data Index: 267982 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1621. Min Act: -0.1700
Data Index: 751279 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1621. Min Act: -0.1700
Data Index: 447652 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1934. Min Act: -0.1700
Data Index: 724292 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1934. Min Act: -0.1700
Data Index: 185516 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1934. Min Act: -0.1700
Data Index: 392551 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1621. Min Act: -0.1700
Data Index: 445587 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1934. Min Act: -0.1700
Data Index: 686062 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.0996. Min Act: -0.1700
Data Index: 797821 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.0996. Min Act: -0.1700
Data Index: 1358362 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1308. Min Act: -0.1700
Data Index: 163939 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1308. Min Act: -0.1700
Data Index: 709336 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.0996. Min Act: -0.1700
Data Index: 689124 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3809. Min Range: -4.3809
Max Act: 4.1308. Min Act: -0.1700
Data Index: 918608 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19