Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 22 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.9527. Min Act: -0.1700
Data Index: 1361790 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.8735. Min Act: -0.1700
Data Index: 1243707 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.8258. Min Act: -0.1700
Data Index: 1431143 (Python Code)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.7621. Min Act: -0.1700
Data Index: 271796 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.7461. Min Act: -0.1700
Data Index: 1370891 (Python Code)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.7301. Min Act: -0.1700
Data Index: 1390291 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.7141. Min Act: -0.1700
Data Index: 112729 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6981. Min Act: -0.1700
Data Index: 1523025 (Python Code)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6981. Min Act: -0.1700
Data Index: 532045 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6821. Min Act: -0.1700
Data Index: 1506190 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6821. Min Act: -0.1700
Data Index: 596852 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6661. Min Act: -0.1700
Data Index: 233414 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6501. Min Act: -0.1700
Data Index: 1345298 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6501. Min Act: -0.1700
Data Index: 1416966 (Python Code)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6501. Min Act: -0.1700
Data Index: 1529992 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6501. Min Act: -0.1700
Data Index: 1617851 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6340. Min Act: -0.1700
Data Index: 1041998 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6340. Min Act: -0.1700
Data Index: 1455613 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6340. Min Act: -0.1700
Data Index: 1451958 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9527. Min Range: -2.9527
Max Act: 2.6340. Min Act: -0.1700
Data Index: 1447557 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19