Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1413 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.5185. Min Act: -0.1700
Data Index: 230160 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.5185. Min Act: -0.1700
Data Index: 430300 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4560. Min Act: -0.1700
Data Index: 463930 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4560. Min Act: -0.1700
Data Index: 957996 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4560. Min Act: -0.1700
Data Index: 410800 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4560. Min Act: -0.1700
Data Index: 307309 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4247. Min Act: -0.1700
Data Index: 202003 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4560. Min Act: -0.1700
Data Index: 629446 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4247. Min Act: -0.1700
Data Index: 397507 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3935. Min Act: -0.1700
Data Index: 1337729 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4247. Min Act: -0.1700
Data Index: 1289053 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.4247. Min Act: -0.1700
Data Index: 202034 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3310. Min Act: -0.1700
Data Index: 331415 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3622. Min Act: -0.1700
Data Index: 63441 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3622. Min Act: -0.1700
Data Index: 905765 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3622. Min Act: -0.1700
Data Index: 1063450 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3935. Min Act: -0.1700
Data Index: 79948 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3622. Min Act: -0.1700
Data Index: 1081687 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3935. Min Act: -0.1700
Data Index: 57941 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5185. Min Range: -4.5185
Max Act: 4.3622. Min Act: -0.1700
Data Index: 288654 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19