Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 37 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.6967. Min Act: -0.1700
Data Index: 1000979 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.5092. Min Act: -0.1700
Data Index: 146245 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.4467. Min Act: -0.1700
Data Index: 1271182 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.3529. Min Act: -0.1700
Data Index: 1040659 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.3842. Min Act: -0.1700
Data Index: 872921 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.3529. Min Act: -0.1700
Data Index: 207306 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.3529. Min Act: -0.1700
Data Index: 270507 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.3217. Min Act: -0.1700
Data Index: 62162 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 724436 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2904. Min Act: -0.1700
Data Index: 560925 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 1309675 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.1967. Min Act: -0.1700
Data Index: 98152 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 361423 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 267029 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 85979 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 671349 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 573497 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2592. Min Act: -0.1700
Data Index: 251785 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.1967. Min Act: -0.1700
Data Index: 723391 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6967. Min Range: -4.6967
Max Act: 4.2279. Min Act: -0.1700
Data Index: 42031 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19