Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 192 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.8387. Min Act: -0.1700
Data Index: 368274 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.7910. Min Act: -0.1700
Data Index: 489671 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.6791. Min Act: -0.1700
Data Index: 876269 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.5666. Min Act: -0.1700
Data Index: 1299194 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.5666. Min Act: -0.1700
Data Index: 735723 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.5666. Min Act: -0.1700
Data Index: 596697 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.5344. Min Act: -0.1700
Data Index: 207433 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.5182. Min Act: -0.1700
Data Index: 1024848 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4858. Min Act: -0.1700
Data Index: 665088 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.5020. Min Act: -0.1700
Data Index: 919895 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4696. Min Act: -0.1700
Data Index: 542251 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4696. Min Act: -0.1700
Data Index: 1290505 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4696. Min Act: -0.1700
Data Index: 160884 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4533. Min Act: -0.1700
Data Index: 184182 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4371. Min Act: -0.1700
Data Index: 1165861 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4208. Min Act: -0.1700
Data Index: 97915 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4533. Min Act: -0.1700
Data Index: 399629 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4371. Min Act: -0.1700
Data Index: 95934 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4371. Min Act: -0.1700
Data Index: 561757 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8387. Min Range: -2.8387
Max Act: 2.4208. Min Act: -0.1700
Data Index: 760015 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19