Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 304 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7838. Min Act: -0.1700
Data Index: 1170158 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7519. Min Act: -0.1700
Data Index: 1017369 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7679. Min Act: -0.1700
Data Index: 450083 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7359. Min Act: -0.1700
Data Index: 246531 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7200. Min Act: -0.1700
Data Index: 1447682 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7200. Min Act: -0.1700
Data Index: 527851 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7359. Min Act: -0.1700
Data Index: 230936 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7200. Min Act: -0.1700
Data Index: 1321516 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 741636 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7200. Min Act: -0.1700
Data Index: 903381 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 341217 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7200. Min Act: -0.1700
Data Index: 1357964 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7200. Min Act: -0.1700
Data Index: 686062 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.6880. Min Act: -0.1700
Data Index: 142114 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 1131258 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 1131685 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 331298 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 1152678 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.7040. Min Act: -0.1700
Data Index: 605611 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7838. Min Range: -2.7838
Max Act: 2.6880. Min Act: -0.1700
Data Index: 337909 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19