Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 117 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.2571. Min Act: -0.1700
Data Index: 431333 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.3508. Min Act: -0.1700
Data Index: 683849 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.1633. Min Act: -0.1700
Data Index: 503908 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.1633. Min Act: -0.1700
Data Index: 926974 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.2571. Min Act: -0.1700
Data Index: 947830 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.1633. Min Act: -0.1700
Data Index: 990801 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.0383. Min Act: -0.1700
Data Index: 702762 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9758. Min Act: -0.1700
Data Index: 737805 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.8821. Min Act: -0.1700
Data Index: 1086643 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.8508. Min Act: -0.1700
Data Index: 1239015 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9446. Min Act: -0.1700
Data Index: 444886 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3508. Min Range: -5.3508
Max Act: 5.0696. Min Act: -0.1700
Data Index: 275822 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9758. Min Act: -0.1700
Data Index: 806089 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9446. Min Act: -0.1700
Data Index: 31883 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9446. Min Act: -0.1700
Data Index: 1174199 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9758. Min Act: -0.1700
Data Index: 1055877 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.9133. Min Act: -0.1700
Data Index: 970817 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.8508. Min Act: -0.1700
Data Index: 555707 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.8196. Min Act: -0.1700
Data Index: 316294 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3508. Min Range: -5.3508
Max Act: 4.7883. Min Act: -0.1700
Data Index: 1221693 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19