Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 654 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.7082. Min Act: -0.1700
Data Index: 991568 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.7707. Min Act: -0.1700
Data Index: 563906 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.6144. Min Act: -0.1700
Data Index: 161291 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5519. Min Act: -0.1700
Data Index: 19249 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.6457. Min Act: -0.1700
Data Index: 248334 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5519. Min Act: -0.1700
Data Index: 1213864 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5207. Min Act: -0.1700
Data Index: 1316614 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5832. Min Act: -0.1700
Data Index: 83793 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5519. Min Act: -0.1700
Data Index: 445221 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.3957. Min Act: -0.1700
Data Index: 1259975 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5207. Min Act: -0.1700
Data Index: 366393 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.5519. Min Act: -0.1700
Data Index: 889106 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4894. Min Act: -0.1700
Data Index: 354265 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4894. Min Act: -0.1700
Data Index: 1104939 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4269. Min Act: -0.1700
Data Index: 262538 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4894. Min Act: -0.1700
Data Index: 289625 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4894. Min Act: -0.1700
Data Index: 1079976 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4582. Min Act: -0.1700
Data Index: 124628 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.3957. Min Act: -0.1700
Data Index: 570738 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7707. Min Range: -4.7707
Max Act: 4.4269. Min Act: -0.1700
Data Index: 267534 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19