Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1347 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.9164. Min Act: -0.1700
Data Index: 531335 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.7414. Min Act: -0.1700
Data Index: 164601 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.7414. Min Act: -0.1700
Data Index: 551229 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.7255. Min Act: -0.1700
Data Index: 1043891 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.7095. Min Act: -0.1700
Data Index: 254557 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.7095. Min Act: -0.1700
Data Index: 340118 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6935. Min Act: -0.1700
Data Index: 229478 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6935. Min Act: -0.1700
Data Index: 510466 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6935. Min Act: -0.1700
Data Index: 1304542 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6935. Min Act: -0.1700
Data Index: 671128 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6935. Min Act: -0.1700
Data Index: 597266 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6775. Min Act: -0.1700
Data Index: 317101 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6614. Min Act: -0.1700
Data Index: 1037701 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6775. Min Act: -0.1700
Data Index: 910073 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6614. Min Act: -0.1700
Data Index: 802220 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6614. Min Act: -0.1700
Data Index: 334375 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6614. Min Act: -0.1700
Data Index: 646829 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6454. Min Act: -0.1700
Data Index: 271178 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6293. Min Act: -0.1700
Data Index: 566785 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9164. Min Range: -2.9164
Max Act: 2.6454. Min Act: -0.1700
Data Index: 672554 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19