Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.8459. Min Act: -0.1700
Data Index: 1300295 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.9084. Min Act: -0.1700
Data Index: 186878 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.8772. Min Act: -0.1700
Data Index: 1164794 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.7834. Min Act: -0.1700
Data Index: 49763 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.6897. Min Act: -0.1700
Data Index: 281070 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.6897. Min Act: -0.1700
Data Index: 719304 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.7209. Min Act: -0.1700
Data Index: 1041491 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.6897. Min Act: -0.1699
Data Index: 1245058 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.6272. Min Act: -0.1700
Data Index: 326039 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5647. Min Act: -0.1700
Data Index: 314344 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5959. Min Act: -0.1700
Data Index: 262773 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5959. Min Act: -0.1699
Data Index: 769229 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5647. Min Act: -0.1700
Data Index: 810609 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5959. Min Act: -0.1700
Data Index: 993656 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5959. Min Act: -0.1700
Data Index: 1170950 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5647. Min Act: -0.1700
Data Index: 477430 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5022. Min Act: -0.1700
Data Index: 263612 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5647. Min Act: -0.1700
Data Index: 956311 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5334. Min Act: -0.1700
Data Index: 1230772 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9084. Min Range: -4.9084
Max Act: 4.5334. Min Act: -0.1700
Data Index: 1086602 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19