Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 171 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.0187. Min Range: -2.0187
Max Act: 2.0187. Min Act: -0.1700
Data Index: 287332 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0187. Min Range: -2.0187
Max Act: 2.0103. Min Act: -0.1700
Data Index: 1580695 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.9426. Min Act: -0.1700
Data Index: 335819 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.9426. Min Act: -0.1700
Data Index: 317405 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8915. Min Act: -0.1700
Data Index: 1041314 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8915. Min Act: -0.1700
Data Index: 1151773 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8745. Min Act: -0.1700
Data Index: 385152 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8574. Min Act: -0.1700
Data Index: 748205 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8488. Min Act: -0.1700
Data Index: 150086 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8402. Min Act: -0.1700
Data Index: 396008 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8145. Min Act: -0.1700
Data Index: 1457468 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8145. Min Act: -0.1700
Data Index: 1133874 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8231. Min Act: -0.1700
Data Index: 223180 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8145. Min Act: -0.1700
Data Index: 148203 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8059. Min Act: -0.1700
Data Index: 291684 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.8059. Min Act: -0.1700
Data Index: 680853 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.7973. Min Act: -0.1700
Data Index: 850728 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.7973. Min Act: -0.1700
Data Index: 1234695 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.7887. Min Act: -0.1700
Data Index: 1017735 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0187. Min Range: -2.0187
Max Act: 1.7801. Min Act: -0.1700
Data Index: 761573 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19