Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1161 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.4018. Min Act: -0.1700
Data Index: 1102946 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.4018. Min Act: -0.1700
Data Index: 232188 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3854. Min Act: -0.1700
Data Index: 601565 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3854. Min Act: -0.1700
Data Index: 1263816 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3691. Min Act: -0.1700
Data Index: 1320802 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3527. Min Act: -0.1700
Data Index: 269490 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3527. Min Act: -0.1700
Data Index: 671161 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3527. Min Act: -0.1700
Data Index: 784603 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3527. Min Act: -0.1700
Data Index: 877836 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3364. Min Act: -0.1700
Data Index: 1482370 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3364. Min Act: -0.1700
Data Index: 610003 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3364. Min Act: -0.1700
Data Index: 399433 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3364. Min Act: -0.1700
Data Index: 811229 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3364. Min Act: -0.1700
Data Index: 283091 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3364. Min Act: -0.1700
Data Index: 399207 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3200. Min Act: -0.1700
Data Index: 665888 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3200. Min Act: -0.1700
Data Index: 12945 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3200. Min Act: -0.1700
Data Index: 727296 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3200. Min Act: -0.1700
Data Index: 782855 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4018. Min Range: -2.4018
Max Act: 2.3200. Min Act: -0.1700
Data Index: 202755 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19