Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2047 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.7214. Min Act: -0.1700
Data Index: 592378 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6894. Min Act: -0.1700
Data Index: 602811 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6894. Min Act: -0.1700
Data Index: 1262616 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.7054. Min Act: -0.1700
Data Index: 322753 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.7214. Min Act: -0.1700
Data Index: 1206371 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6734. Min Act: -0.1700
Data Index: 1090343 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6734. Min Act: -0.1700
Data Index: 462082 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6413. Min Act: -0.1700
Data Index: 275251 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6413. Min Act: -0.1700
Data Index: 183075 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6413. Min Act: -0.1700
Data Index: 418133 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6252. Min Act: -0.1700
Data Index: 1182702 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.6252. Min Act: -0.1700
Data Index: 28438 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5931. Min Act: -0.1700
Data Index: 157756 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5447. Min Act: -0.1700
Data Index: 89310 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5285. Min Act: -0.1700
Data Index: 522693 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5285. Min Act: -0.1700
Data Index: 295718 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5124. Min Act: -0.1700
Data Index: 646192 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5285. Min Act: -0.1700
Data Index: 279614 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5447. Min Act: -0.1700
Data Index: 952531 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7214. Min Range: -2.7214
Max Act: 2.5124. Min Act: -0.1700
Data Index: 1599117 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19