Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 27 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.8433. Min Act: -0.1700
Data Index: 190820 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.8274. Min Act: -0.1700
Data Index: 1161579 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.8274. Min Act: -0.1700
Data Index: 1128683 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.8274. Min Act: -0.1700
Data Index: 221956 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7956. Min Act: -0.1700
Data Index: 1031363 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.8274. Min Act: -0.1700
Data Index: 46552 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7956. Min Act: -0.1700
Data Index: 1356727 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7956. Min Act: -0.1700
Data Index: 507645 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 655091 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 961791 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 1300526 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 28835 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7956. Min Act: -0.1700
Data Index: 462492 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 1275873 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7956. Min Act: -0.1700
Data Index: 83346 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 827684 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7956. Min Act: -0.1700
Data Index: 964576 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 704380 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 325092 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8433. Min Range: -2.8433
Max Act: 2.7796. Min Act: -0.1700
Data Index: 1103695 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19