Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 135 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1437. Min Range: -4.1437
Max Act: 4.1437. Min Act: -0.1700
Data Index: 506650 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1437. Min Range: -4.1437
Max Act: 4.1124. Min Act: -0.1700
Data Index: 380591 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1437. Min Range: -4.1437
Max Act: 4.0812. Min Act: -0.1700
Data Index: 657732 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1437. Min Range: -4.1437
Max Act: 4.0186. Min Act: -0.1700
Data Index: 731116 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1437. Min Range: -4.1437
Max Act: 4.0499. Min Act: -0.1700
Data Index: 949236 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.9874. Min Act: -0.1700
Data Index: 34962 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.9561. Min Act: -0.1700
Data Index: 1171298 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8936. Min Act: -0.1700
Data Index: 1152245 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.9248. Min Act: -0.1700
Data Index: 1305037 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.9248. Min Act: -0.1700
Data Index: 72764 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.9248. Min Act: -0.1700
Data Index: 756263 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8936. Min Act: -0.1700
Data Index: 1199590 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8623. Min Act: -0.1700
Data Index: 761032 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8936. Min Act: -0.1700
Data Index: 619249 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8936. Min Act: -0.1700
Data Index: 1118300 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8623. Min Act: -0.1700
Data Index: 639701 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8623. Min Act: -0.1700
Data Index: 626937 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8310. Min Act: -0.1700
Data Index: 456163 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.8310. Min Act: -0.1700
Data Index: 266157 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1437. Min Range: -4.1437
Max Act: 3.7997. Min Act: -0.1700
Data Index: 1096202 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19