Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1282 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.6633. Min Act: -0.1700
Data Index: 387278 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.6312. Min Act: -0.1700
Data Index: 826282 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5991. Min Act: -0.1700
Data Index: 1349936 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5830. Min Act: -0.1700
Data Index: 137265 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5668. Min Act: -0.1700
Data Index: 1528710 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5830. Min Act: -0.1700
Data Index: 1122455 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5668. Min Act: -0.1700
Data Index: 229691 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5507. Min Act: -0.1700
Data Index: 782886 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5507. Min Act: -0.1700
Data Index: 1453414 (Python Code)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5507. Min Act: -0.1700
Data Index: 1424894 (Python Code)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5184. Min Act: -0.1700
Data Index: 518658 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5346. Min Act: -0.1700
Data Index: 944451 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5184. Min Act: -0.1700
Data Index: 841100 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5346. Min Act: -0.1700
Data Index: 693974 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5346. Min Act: -0.1700
Data Index: 1551905 (Python Code)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5346. Min Act: -0.1700
Data Index: 1284851 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.5184. Min Act: -0.1700
Data Index: 400702 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.4860. Min Act: -0.1700
Data Index: 1252885 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.4860. Min Act: -0.1700
Data Index: 59236 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6633. Min Range: -2.6633
Max Act: 2.4698. Min Act: -0.1700
Data Index: 327268 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19