Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1435 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.4368. Min Act: -0.1700
Data Index: 1434511 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.2493. Min Act: -0.1700
Data Index: 361273 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.3118. Min Act: -0.1700
Data Index: 1597493 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1868. Min Act: -0.1700
Data Index: 1274270 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.2181. Min Act: -0.1700
Data Index: 522448 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1868. Min Act: -0.1700
Data Index: 1421090 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1243. Min Act: -0.1700
Data Index: 58617 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1243. Min Act: -0.1700
Data Index: 809914 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1243. Min Act: -0.1700
Data Index: 451458 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0930. Min Act: -0.1699
Data Index: 612766 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1243. Min Act: -0.1699
Data Index: 61859 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0930. Min Act: -0.1700
Data Index: 740324 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.1243. Min Act: -0.1700
Data Index: 337128 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0930. Min Act: -0.1700
Data Index: 37685 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4368. Min Range: -4.4368
Max Act: 3.9367. Min Act: -0.1700
Data Index: 676525 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0305. Min Act: -0.1700
Data Index: 672609 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0930. Min Act: -0.1700
Data Index: 1188830 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0618. Min Act: -0.1700
Data Index: 668857 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4368. Min Range: -4.4368
Max Act: 3.9992. Min Act: -0.1700
Data Index: 1114826 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4368. Min Range: -4.4368
Max Act: 4.0930. Min Act: -0.1700
Data Index: 1239734 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19