Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1711 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1104. Min Range: -4.1104
Max Act: 4.1104. Min Act: -0.1700
Data Index: 993421 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.9540. Min Act: -0.1700
Data Index: 784602 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.9540. Min Act: -0.1700
Data Index: 996591 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.8915. Min Act: -0.1700
Data Index: 392110 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.8602. Min Act: -0.1700
Data Index: 905344 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7977. Min Act: -0.1700
Data Index: 1503859 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7977. Min Act: -0.1700
Data Index: 496814 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7977. Min Act: -0.1700
Data Index: 1248362 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.8290. Min Act: -0.1700
Data Index: 584070 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7977. Min Act: -0.1700
Data Index: 502235 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7664. Min Act: -0.1700
Data Index: 683415 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7351. Min Act: -0.1700
Data Index: 965804 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7038. Min Act: -0.1700
Data Index: 40678 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7351. Min Act: -0.1700
Data Index: 645718 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7664. Min Act: -0.1700
Data Index: 133247 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7351. Min Act: -0.1700
Data Index: 1231226 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7664. Min Act: -0.1700
Data Index: 1557052 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7038. Min Act: -0.1700
Data Index: 1330033 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.7038. Min Act: -0.1700
Data Index: 102469 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1104. Min Range: -4.1104
Max Act: 3.6725. Min Act: -0.1700
Data Index: 1041250 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19