Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 319 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0940. Min Range: -3.0940
Max Act: 3.0940. Min Act: -0.1700
Data Index: 534706 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0940. Min Range: -3.0940
Max Act: 3.0782. Min Act: -0.1700
Data Index: 190803 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0940. Min Range: -3.0940
Max Act: 3.0308. Min Act: -0.1700
Data Index: 1286766 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0940. Min Range: -3.0940
Max Act: 3.0150. Min Act: -0.1700
Data Index: 1194528 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9834. Min Act: -0.1700
Data Index: 1113699 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0940. Min Range: -3.0940
Max Act: 3.0150. Min Act: -0.1700
Data Index: 456789 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9834. Min Act: -0.1700
Data Index: 1082170 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9834. Min Act: -0.1700
Data Index: 698234 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9359. Min Act: -0.1700
Data Index: 1514400 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9201. Min Act: -0.1700
Data Index: 31938 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9359. Min Act: -0.1700
Data Index: 521723 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9042. Min Act: -0.1700
Data Index: 973639 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8884. Min Act: -0.1700
Data Index: 396226 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.9042. Min Act: -0.1700
Data Index: 420855 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8884. Min Act: -0.1700
Data Index: 1191879 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8884. Min Act: -0.1700
Data Index: 832576 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8725. Min Act: -0.1700
Data Index: 661467 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8407. Min Act: -0.1700
Data Index: 744458 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8407. Min Act: -0.1700
Data Index: 1363845 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0940. Min Range: -3.0940
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1580627 (Python Code)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19