Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1539 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.9920. Min Act: -0.1700
Data Index: 281488 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.9287. Min Act: -0.1700
Data Index: 166252 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8970. Min Act: -0.1700
Data Index: 380989 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8970. Min Act: -0.1700
Data Index: 10175 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8653. Min Act: -0.1700
Data Index: 129154 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8970. Min Act: -0.1700
Data Index: 1087549 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8811. Min Act: -0.1700
Data Index: 1012361 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8335. Min Act: -0.1700
Data Index: 424613 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8494. Min Act: -0.1700
Data Index: 876026 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8176. Min Act: -0.1700
Data Index: 774710 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8176. Min Act: -0.1700
Data Index: 1015638 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8016. Min Act: -0.1700
Data Index: 161195 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8176. Min Act: -0.1700
Data Index: 73346 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.7857. Min Act: -0.1700
Data Index: 1297648 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8176. Min Act: -0.1700
Data Index: 806213 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8176. Min Act: -0.1700
Data Index: 1796 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.8016. Min Act: -0.1700
Data Index: 333654 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.7698. Min Act: -0.1700
Data Index: 532405 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.7857. Min Act: -0.1700
Data Index: 696095 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9920. Min Range: -2.9920
Max Act: 2.7857. Min Act: -0.1700
Data Index: 489059 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19