Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 71 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.8565. Min Act: -0.1700
Data Index: 1209728 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.8253. Min Act: -0.1700
Data Index: 1118759 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.8565. Min Act: -0.1700
Data Index: 147724 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.8253. Min Act: -0.1700
Data Index: 836379 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.8253. Min Act: -0.1700
Data Index: 1324543 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7940. Min Act: -0.1700
Data Index: 1228831 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7940. Min Act: -0.1700
Data Index: 1039244 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7315. Min Act: -0.1700
Data Index: 225372 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7940. Min Act: -0.1700
Data Index: 572921 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7315. Min Act: -0.1700
Data Index: 1012871 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7315. Min Act: -0.1700
Data Index: 641826 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7003. Min Act: -0.1700
Data Index: 495083 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7315. Min Act: -0.1700
Data Index: 1095959 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.6378. Min Act: -0.1700
Data Index: 40052 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.6690. Min Act: -0.1700
Data Index: 943604 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7003. Min Act: -0.1700
Data Index: 172831 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.6690. Min Act: -0.1700
Data Index: 503284 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7003. Min Act: -0.1700
Data Index: 1199058 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.7003. Min Act: -0.1700
Data Index: 502948 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8565. Min Range: -4.8565
Max Act: 4.6065. Min Act: -0.1700
Data Index: 890792 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19