Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 605 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1799. Min Act: -0.1700
Data Index: 699514 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1957. Min Act: -0.1700
Data Index: 294630 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1169. Min Act: -0.1700
Data Index: 1053424 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1484. Min Act: -0.1700
Data Index: 158753 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1169. Min Act: -0.1700
Data Index: 260988 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0696. Min Act: -0.1700
Data Index: 281934 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0854. Min Act: -0.1700
Data Index: 406022 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0538. Min Act: -0.1700
Data Index: 583664 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0538. Min Act: -0.1700
Data Index: 419649 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0696. Min Act: -0.1700
Data Index: 418140 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0381. Min Act: -0.1700
Data Index: 248778 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0381. Min Act: -0.1700
Data Index: 225716 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0538. Min Act: -0.1700
Data Index: 635746 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0381. Min Act: -0.1700
Data Index: 654375 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0381. Min Act: -0.1700
Data Index: 933384 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0538. Min Act: -0.1700
Data Index: 41144 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0223. Min Act: -0.1700
Data Index: 321755 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0223. Min Act: -0.1700
Data Index: 9914 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0381. Min Act: -0.1700
Data Index: 745808 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0065. Min Act: -0.1700
Data Index: 832275 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19