Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2046 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.3106. Min Act: -0.1700
Data Index: 1258931 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.1387. Min Act: -0.1700
Data Index: 599437 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.1387. Min Act: -0.1700
Data Index: 768707 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.1075. Min Act: -0.1699
Data Index: 641574 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.0918. Min Act: -0.1700
Data Index: 947179 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.0137. Min Act: -0.1700
Data Index: 110546 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.0606. Min Act: -0.1700
Data Index: 1294779 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.0137. Min Act: -0.1700
Data Index: 5588 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9824. Min Act: -0.1700
Data Index: 1237028 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9980. Min Act: -0.1700
Data Index: 518479 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9824. Min Act: -0.1700
Data Index: 217629 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3106. Min Range: -4.3106
Max Act: 4.0137. Min Act: -0.1700
Data Index: 685439 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9980. Min Act: -0.1700
Data Index: 572198 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9511. Min Act: -0.1700
Data Index: 1030820 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9511. Min Act: -0.1700
Data Index: 1322909 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9511. Min Act: -0.1700
Data Index: 709615 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9511. Min Act: -0.1700
Data Index: 394505 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9511. Min Act: -0.1700
Data Index: 629521 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.9199. Min Act: -0.1700
Data Index: 907272 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3106. Min Range: -4.3106
Max Act: 3.8886. Min Act: -0.1700
Data Index: 910597 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19