Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1267 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.5341. Min Act: -0.1700
Data Index: 826815 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.4855. Min Act: -0.1700
Data Index: 1195798 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.4042. Min Act: -0.1700
Data Index: 106177 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.3879. Min Act: -0.1700
Data Index: 912309 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.3224. Min Act: -0.1700
Data Index: 457387 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.3224. Min Act: -0.1700
Data Index: 1618501 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.3224. Min Act: -0.1700
Data Index: 833355 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.3060. Min Act: -0.1699
Data Index: 1647911 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.3060. Min Act: -0.1696
Data Index: 1591846 (Python Code)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2895. Min Act: -0.1700
Data Index: 133419 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2895. Min Act: -0.1700
Data Index: 1476102 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2895. Min Act: -0.1700
Data Index: 1493169 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2731. Min Act: -0.1700
Data Index: 1514638 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2566. Min Act: -0.1700
Data Index: 1491412 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2731. Min Act: -0.1700
Data Index: 1403585 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2731. Min Act: -0.1638
Data Index: 1571088 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2731. Min Act: -0.1700
Data Index: 1616432 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2731. Min Act: -0.1700
Data Index: 1469531 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2566. Min Act: -0.1700
Data Index: 1463356 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5341. Min Range: -2.5341
Max Act: 2.2401. Min Act: -0.1700
Data Index: 920152 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19