Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 854 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8660. Min Act: -0.1700
Data Index: 816295 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8660. Min Act: -0.1700
Data Index: 1479846 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 467922 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 1059189 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 59739 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 480986 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 1397277 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 452082 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8342. Min Act: -0.1700
Data Index: 1316446 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8342. Min Act: -0.1700
Data Index: 1042549 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8342. Min Act: -0.1700
Data Index: 1429293 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8183. Min Act: -0.1700
Data Index: 1620470 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8501. Min Act: -0.1700
Data Index: 1512464 (Python Code)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8342. Min Act: -0.1700
Data Index: 826335 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8183. Min Act: -0.1700
Data Index: 1221350 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8342. Min Act: -0.1700
Data Index: 472836 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8183. Min Act: -0.1700
Data Index: 317663 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8183. Min Act: -0.1700
Data Index: 1019745 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.8183. Min Act: -0.1700
Data Index: 652494 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8660. Min Range: -2.8660
Max Act: 2.7865. Min Act: -0.1700
Data Index: 1035707 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19