Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1378 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6957. Min Act: -0.1700
Data Index: 1343785 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6957. Min Act: -0.1700
Data Index: 181155 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6797. Min Act: -0.1700
Data Index: 839846 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 163325 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6797. Min Act: -0.1700
Data Index: 1039793 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6797. Min Act: -0.1700
Data Index: 1158416 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 1210054 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6797. Min Act: -0.1700
Data Index: 765830 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6797. Min Act: -0.1700
Data Index: 321752 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6797. Min Act: -0.1700
Data Index: 34080 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 96242 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 299969 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 306836 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6476. Min Act: -0.1700
Data Index: 17657 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 315468 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 338078 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6476. Min Act: -0.1700
Data Index: 376824 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 385272 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 89416 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6957. Min Range: -2.6957
Max Act: 2.6636. Min Act: -0.1700
Data Index: 412275 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19