Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 49 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.8102. Min Act: -0.1700
Data Index: 244643 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.8102. Min Act: -0.1700
Data Index: 1293751 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.8102. Min Act: -0.1700
Data Index: 244951 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7789. Min Act: -0.1700
Data Index: 1222152 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7789. Min Act: -0.1700
Data Index: 574146 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.8102. Min Act: -0.1700
Data Index: 175803 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7789. Min Act: -0.1700
Data Index: 1076162 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7477. Min Act: -0.1700
Data Index: 750294 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7789. Min Act: -0.1700
Data Index: 693830 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7477. Min Act: -0.1700
Data Index: 324697 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.6852. Min Act: -0.1700
Data Index: 66231 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7477. Min Act: -0.1700
Data Index: 109998 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7164. Min Act: -0.1700
Data Index: 786968 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7477. Min Act: -0.1700
Data Index: 175920 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7789. Min Act: -0.1700
Data Index: 784874 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.6852. Min Act: -0.1700
Data Index: 245394 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.6539. Min Act: -0.1700
Data Index: 458846 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7164. Min Act: -0.1700
Data Index: 916581 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.7164. Min Act: -0.1700
Data Index: 1142944 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8102. Min Range: -4.8102
Max Act: 4.6852. Min Act: -0.1700
Data Index: 237258 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19