Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1458 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0567. Min Range: -4.0567
Max Act: 4.0255. Min Act: -0.1700
Data Index: 372731 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0567. Min Range: -4.0567
Max Act: 4.0567. Min Act: -0.1700
Data Index: 282398 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0567. Min Range: -4.0567
Max Act: 4.0255. Min Act: -0.1700
Data Index: 1083831 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0567. Min Range: -4.0567
Max Act: 4.0255. Min Act: -0.1700
Data Index: 812102 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9629. Min Act: -0.1700
Data Index: 1272597 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9316. Min Act: -0.1700
Data Index: 666942 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9316. Min Act: -0.1700
Data Index: 337160 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9316. Min Act: -0.1700
Data Index: 609094 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9004. Min Act: -0.1700
Data Index: 931379 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9316. Min Act: -0.1700
Data Index: 473231 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9316. Min Act: -0.1700
Data Index: 1332925 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 1084587 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 845405 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9004. Min Act: -0.1700
Data Index: 1211228 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 1125224 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.9004. Min Act: -0.1700
Data Index: 129873 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 739276 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 256047 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 875616 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0567. Min Range: -4.0567
Max Act: 3.8691. Min Act: -0.1700
Data Index: 184989 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19