Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1854 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4330. Min Act: -0.1700
Data Index: 860069 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4330. Min Act: -0.1700
Data Index: 224533 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4330. Min Act: -0.1700
Data Index: 389173 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4330. Min Act: -0.1700
Data Index: 14446 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4017. Min Act: -0.1700
Data Index: 668418 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4017. Min Act: -0.1700
Data Index: 901858 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.4017. Min Act: -0.1700
Data Index: 500060 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3705. Min Act: -0.1700
Data Index: 1327925 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3705. Min Act: -0.1700
Data Index: 56860 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3392. Min Act: -0.1700
Data Index: 973486 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3080. Min Act: -0.1700
Data Index: 130458 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3080. Min Act: -0.1700
Data Index: 669766 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3080. Min Act: -0.1700
Data Index: 1320284 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3080. Min Act: -0.1700
Data Index: 502547 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3392. Min Act: -0.1700
Data Index: 529961 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3080. Min Act: -0.1700
Data Index: 1114311 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3080. Min Act: -0.1700
Data Index: 562871 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.2767. Min Act: -0.1700
Data Index: 35036 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.2767. Min Act: -0.1700
Data Index: 848220 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4330. Min Range: -4.4330
Max Act: 4.3392. Min Act: -0.1700
Data Index: 870888 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19