Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 230 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0239. Min Range: -4.0239
Max Act: 4.0239. Min Act: -0.1700
Data Index: 1059138 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0239. Min Range: -4.0239
Max Act: 4.0239. Min Act: -0.1700
Data Index: 308870 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.9301. Min Act: -0.1700
Data Index: 1260689 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.9301. Min Act: -0.1700
Data Index: 1307094 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8988. Min Act: -0.1700
Data Index: 611190 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8988. Min Act: -0.1700
Data Index: 1196505 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8988. Min Act: -0.1700
Data Index: 118685 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.9301. Min Act: -0.1700
Data Index: 175010 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8988. Min Act: -0.1700
Data Index: 1084644 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8988. Min Act: -0.1700
Data Index: 680490 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.9301. Min Act: -0.1700
Data Index: 1158611 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8676. Min Act: -0.1700
Data Index: 421380 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.9301. Min Act: -0.1700
Data Index: 445043 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.9614. Min Act: -0.1700
Data Index: 95666 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8363. Min Act: -0.1700
Data Index: 283529 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8988. Min Act: -0.1700
Data Index: 812565 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8363. Min Act: -0.1700
Data Index: 187055 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8676. Min Act: -0.1700
Data Index: 780129 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8050. Min Act: -0.1700
Data Index: 1095239 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0239. Min Range: -4.0239
Max Act: 3.8050. Min Act: -0.1700
Data Index: 832938 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19