Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 253 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.3119. Min Act: -0.1700
Data Index: 624414 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.2790. Min Act: -0.1700
Data Index: 1107883 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.2460. Min Act: -0.1700
Data Index: 1224595 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.2295. Min Act: -0.1700
Data Index: 661539 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1964. Min Act: -0.1700
Data Index: 1074882 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1964. Min Act: -0.1700
Data Index: 96086 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1964. Min Act: -0.1700
Data Index: 763151 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1964. Min Act: -0.1700
Data Index: 1229217 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1964. Min Act: -0.1700
Data Index: 1178715 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1798. Min Act: -0.1700
Data Index: 104009 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1964. Min Act: -0.1700
Data Index: 650957 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1798. Min Act: -0.1700
Data Index: 333050 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1631. Min Act: -0.1699
Data Index: 345685 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1631. Min Act: -0.1700
Data Index: 449165 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1631. Min Act: -0.1700
Data Index: 51433 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1631. Min Act: -0.1700
Data Index: 1073901 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1798. Min Act: -0.1700
Data Index: 302687 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1465. Min Act: -0.1700
Data Index: 939649 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1465. Min Act: -0.1700
Data Index: 569655 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3119. Min Range: -2.3119
Max Act: 2.1465. Min Act: -0.1700
Data Index: 297327 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19