Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.4272. Min Act: -0.1700
Data Index: 31900 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.2709. Min Act: -0.1700
Data Index: 593113 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.2396. Min Act: -0.1700
Data Index: 1251939 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.2396. Min Act: -0.1700
Data Index: 1081098 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.2084. Min Act: -0.1700
Data Index: 1023533 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1771. Min Act: -0.1700
Data Index: 466586 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1771. Min Act: -0.1700
Data Index: 704881 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1771. Min Act: -0.1700
Data Index: 67058 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1459. Min Act: -0.1700
Data Index: 959067 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.2084. Min Act: -0.1700
Data Index: 924206 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1771. Min Act: -0.1700
Data Index: 923421 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1771. Min Act: -0.1700
Data Index: 1228115 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1146. Min Act: -0.1700
Data Index: 8572 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1459. Min Act: -0.1700
Data Index: 979271 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1146. Min Act: -0.1700
Data Index: 214993 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.0833. Min Act: -0.1700
Data Index: 1359575 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1146. Min Act: -0.1700
Data Index: 1133223 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1146. Min Act: -0.1700
Data Index: 684116 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.0833. Min Act: -0.1700
Data Index: 403665 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4272. Min Range: -4.4272
Max Act: 4.1146. Min Act: -0.1700
Data Index: 429698 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19