Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1824 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 177104 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 347622 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 767175 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 915140 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 383122 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 1331396 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 819544 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 56216 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0242. Min Range: -4.0242
Max Act: 4.0242. Min Act: -0.1700
Data Index: 710277 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 971958 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 378392 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 628011 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 678804 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9617. Min Act: -0.1700
Data Index: 944904 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 226797 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9304. Min Act: -0.1700
Data Index: 1311893 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 958319 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 277014 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9617. Min Act: -0.1700
Data Index: 856105 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0242. Min Range: -4.0242
Max Act: 3.9930. Min Act: -0.1700
Data Index: 948619 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19