Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 789 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 1209286 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.8249. Min Act: -0.1700
Data Index: 570738 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.7311. Min Act: -0.1700
Data Index: 334116 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6999. Min Act: -0.1700
Data Index: 778240 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6686. Min Act: -0.1700
Data Index: 1330506 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6999. Min Act: -0.1700
Data Index: 655697 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6686. Min Act: -0.1700
Data Index: 1014164 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6686. Min Act: -0.1700
Data Index: 320757 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6374. Min Act: -0.1700
Data Index: 321532 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1700
Data Index: 1329141 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.6061. Min Act: -0.1700
Data Index: 279157 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5749. Min Act: -0.1700
Data Index: 141805 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.4967. Min Act: -0.1700
Data Index: 239291 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1700
Data Index: 443255 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5749. Min Act: -0.1700
Data Index: 466005 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1700
Data Index: 676785 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1699
Data Index: 1222173 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1700
Data Index: 1323848 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1700
Data Index: 194687 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8561. Min Range: -4.8561
Max Act: 4.5436. Min Act: -0.1700
Data Index: 487846 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19