Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 34 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.2899. Min Act: -0.1700
Data Index: 600960 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.2587. Min Act: -0.1700
Data Index: 1138935 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.2274. Min Act: -0.1700
Data Index: 280238 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.2274. Min Act: -0.1700
Data Index: 411870 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.2274. Min Act: -0.1700
Data Index: 509955 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1649. Min Act: -0.1700
Data Index: 1004315 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 990498 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 123874 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 649277 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 1109972 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 748128 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 542387 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 923323 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1649. Min Act: -0.1700
Data Index: 437741 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1024. Min Act: -0.1700
Data Index: 368016 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1337. Min Act: -0.1700
Data Index: 1086079 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1337. Min Act: -0.1700
Data Index: 42757 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1649. Min Act: -0.1700
Data Index: 790442 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1649. Min Act: -0.1700
Data Index: 598757 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.1962. Min Act: -0.1700
Data Index: 165521 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19