Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 53 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2559. Min Act: -0.1700
Data Index: 913863 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2559. Min Act: -0.1700
Data Index: 343739 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2393. Min Act: -0.1700
Data Index: 498371 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2393. Min Act: -0.1700
Data Index: 1027013 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2228. Min Act: -0.1700
Data Index: 1284491 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2393. Min Act: -0.1700
Data Index: 1059980 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2228. Min Act: -0.1700
Data Index: 269091 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2393. Min Act: -0.1700
Data Index: 754719 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 1556322 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 189802 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 197450 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2228. Min Act: -0.1700
Data Index: 382973 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 1008296 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 621632 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 587715 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.2062. Min Act: -0.1700
Data Index: 61119 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.1897. Min Act: -0.1700
Data Index: 79492 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.1731. Min Act: -0.1700
Data Index: 1231389 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.1897. Min Act: -0.1700
Data Index: 390441 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2559. Min Range: -2.2559
Max Act: 2.1897. Min Act: -0.1700
Data Index: 231697 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19