Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1225 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.3002. Min Act: -0.1700
Data Index: 192598 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.3002. Min Act: -0.1700
Data Index: 1069326 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2689. Min Act: -0.1700
Data Index: 1630947 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2689. Min Act: -0.1700
Data Index: 1249909 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2377. Min Act: -0.1700
Data Index: 1582822 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2377. Min Act: -0.1700
Data Index: 86865 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1751. Min Act: -0.1700
Data Index: 771675 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2064. Min Act: -0.1700
Data Index: 933568 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1751. Min Act: -0.1700
Data Index: 155755 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1751. Min Act: -0.1700
Data Index: 1565750 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2064. Min Act: -0.1700
Data Index: 1628781 (Python Code)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1439. Min Act: -0.1700
Data Index: 721942 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.2064. Min Act: -0.1700
Data Index: 275203 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1439. Min Act: -0.1700
Data Index: 1270822 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1751. Min Act: -0.1700
Data Index: 847375 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1126. Min Act: -0.1700
Data Index: 827993 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1081450 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1439. Min Act: -0.1700
Data Index: 247930 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1439. Min Act: -0.1700
Data Index: 1623355 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3002. Min Range: -4.3002
Max Act: 4.1439. Min Act: -0.1700
Data Index: 986998 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19