Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 851 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.6588. Min Act: -0.1700
Data Index: 1648168 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.6588. Min Act: -0.1700
Data Index: 1640808 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.6275. Min Act: -0.1700
Data Index: 1406701 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5025. Min Act: -0.1700
Data Index: 1438846 (Python Code)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5963. Min Act: -0.1700
Data Index: 1491942 (Python Code)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5963. Min Act: -0.1700
Data Index: 1498749 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5338. Min Act: -0.1700
Data Index: 1450815 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 1631326 (Python Code)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4088. Min Act: -0.1700
Data Index: 1582874 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 1544477 (Python Code)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5025. Min Act: -0.1700
Data Index: 1482394 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5025. Min Act: -0.1700
Data Index: 1431974 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5025. Min Act: -0.1700
Data Index: 1422016 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 1452140 (Python Code)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4400. Min Act: -0.1700
Data Index: 1453341 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4400. Min Act: -0.1700
Data Index: 1578674 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4088. Min Act: -0.1700
Data Index: 1470586 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4088. Min Act: -0.1700
Data Index: 1477070 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 1482196 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.3775. Min Act: -0.1700
Data Index: 1420094 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19