Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1898 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1209. Min Act: -0.1700
Data Index: 597518 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1209. Min Act: -0.1700
Data Index: 827908 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1042. Min Act: -0.1700
Data Index: 909854 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1042. Min Act: -0.1700
Data Index: 132271 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1042. Min Act: -0.1700
Data Index: 144496 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1042. Min Act: -0.1700
Data Index: 1006727 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.1042. Min Act: -0.1700
Data Index: 229446 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0874. Min Act: -0.1700
Data Index: 1260239 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0874. Min Act: -0.1700
Data Index: 937450 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0874. Min Act: -0.1700
Data Index: 993063 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0874. Min Act: -0.1700
Data Index: 845540 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0874. Min Act: -0.1700
Data Index: 1123968 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0707. Min Act: -0.1700
Data Index: 766216 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0707. Min Act: -0.1700
Data Index: 261901 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0539. Min Act: -0.1700
Data Index: 1222075 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0539. Min Act: -0.1700
Data Index: 202112 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0707. Min Act: -0.1700
Data Index: 742003 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0539. Min Act: -0.1700
Data Index: 517305 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0539. Min Act: -0.1700
Data Index: 573273 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1209. Min Range: -2.1209
Max Act: 2.0539. Min Act: -0.1700
Data Index: 60158 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19