Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 94 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.6285. Min Act: -0.1700
Data Index: 977012 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.6124. Min Act: -0.1700
Data Index: 1381060 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5964. Min Act: -0.1700
Data Index: 1404615 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5803. Min Act: -0.1700
Data Index: 1025147 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5803. Min Act: -0.1700
Data Index: 477494 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5480. Min Act: -0.1700
Data Index: 1220552 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5318. Min Act: -0.1700
Data Index: 1382461 (Python Code)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5480. Min Act: -0.1700
Data Index: 1558235 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5480. Min Act: -0.1700
Data Index: 774829 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5157. Min Act: -0.1700
Data Index: 1229369 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5318. Min Act: -0.1700
Data Index: 1483916 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5157. Min Act: -0.1700
Data Index: 1487931 (Python Code)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5318. Min Act: -0.1700
Data Index: 681304 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.4995. Min Act: -0.1700
Data Index: 1483154 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.4995. Min Act: -0.1700
Data Index: 1410264 (Python Code)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5318. Min Act: -0.1700
Data Index: 1488167 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.4995. Min Act: -0.1700
Data Index: 1647997 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.4995. Min Act: -0.1700
Data Index: 937785 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5157. Min Act: -0.1700
Data Index: 1082771 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6285. Min Range: -2.6285
Max Act: 2.5157. Min Act: -0.1700
Data Index: 1153709 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19