Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 562 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.6561. Min Act: -0.1700
Data Index: 405247 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.4061. Min Act: -0.1700
Data Index: 496370 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.3435. Min Act: -0.1700
Data Index: 829373 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.3435. Min Act: -0.1700
Data Index: 545066 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2810. Min Act: -0.1699
Data Index: 937511 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2810. Min Act: -0.1700
Data Index: 997130 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2810. Min Act: -0.1700
Data Index: 395410 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2498. Min Act: -0.1700
Data Index: 1291842 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2185. Min Act: -0.1700
Data Index: 851487 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2185. Min Act: -0.1700
Data Index: 18934 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2185. Min Act: -0.1700
Data Index: 1068629 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2185. Min Act: -0.1700
Data Index: 863552 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.2498. Min Act: -0.1700
Data Index: 694498 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.1873. Min Act: -0.1700
Data Index: 602783 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.1873. Min Act: -0.1700
Data Index: 558671 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.1873. Min Act: -0.1700
Data Index: 1654058 (Python Code)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.1091. Min Act: -0.1700
Data Index: 954051 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.1404. Min Act: -0.1700
Data Index: 289036 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.0935. Min Act: -0.1700
Data Index: 86317 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6561. Min Range: -4.6561
Max Act: 4.1404. Min Act: -0.1700
Data Index: 879484 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19