Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1401 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.7745. Min Act: -0.1700
Data Index: 569105 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.7585. Min Act: -0.1700
Data Index: 614567 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.7745. Min Act: -0.1700
Data Index: 1151449 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.7585. Min Act: -0.1700
Data Index: 1518970 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.7266. Min Act: -0.1700
Data Index: 865805 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.7106. Min Act: -0.1700
Data Index: 1274761 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 1101764 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6946. Min Act: -0.1700
Data Index: 213582 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6946. Min Act: -0.1700
Data Index: 183745 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 1062342 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 372990 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 957982 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 50823 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 1631173 (Python Code)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6626. Min Act: -0.1700
Data Index: 1644228 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6465. Min Act: -0.1700
Data Index: 1655473 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6626. Min Act: -0.1700
Data Index: 1486059 (Python Code)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6465. Min Act: -0.1700
Data Index: 1323016 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6786. Min Act: -0.1700
Data Index: 1007316 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7745. Min Range: -2.7745
Max Act: 2.6626. Min Act: -0.1700
Data Index: 1224151 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19