Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1997 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.4758. Min Act: -0.1700
Data Index: 786248 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.4270. Min Act: -0.1700
Data Index: 437374 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.4107. Min Act: -0.1700
Data Index: 684529 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3781. Min Act: -0.1700
Data Index: 737348 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3944. Min Act: -0.1700
Data Index: 433794 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3781. Min Act: -0.1700
Data Index: 1335265 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3781. Min Act: -0.1700
Data Index: 808527 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3781. Min Act: -0.1700
Data Index: 1106730 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3454. Min Act: -0.1700
Data Index: 755232 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3618. Min Act: -0.1700
Data Index: 1087969 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3454. Min Act: -0.1700
Data Index: 480441 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3454. Min Act: -0.1700
Data Index: 876506 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3454. Min Act: -0.1700
Data Index: 474158 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3126. Min Act: -0.1700
Data Index: 1193226 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3454. Min Act: -0.1700
Data Index: 120565 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3290. Min Act: -0.1700
Data Index: 1005928 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3290. Min Act: -0.1700
Data Index: 406720 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3454. Min Act: -0.1700
Data Index: 830391 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3290. Min Act: -0.1700
Data Index: 1349001 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4758. Min Range: -2.4758
Max Act: 2.3126. Min Act: -0.1700
Data Index: 206280 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19