Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 14 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.6849. Min Act: -0.1700
Data Index: 522960 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.6224. Min Act: -0.1700
Data Index: 1301596 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.4974. Min Act: -0.1700
Data Index: 1178117 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.4661. Min Act: -0.1700
Data Index: 1258271 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.3724. Min Act: -0.1700
Data Index: 840714 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.3724. Min Act: -0.1700
Data Index: 608946 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.4036. Min Act: -0.1700
Data Index: 1205802 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.3099. Min Act: -0.1700
Data Index: 1346996 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.2161. Min Act: -0.1700
Data Index: 1228042 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.1536. Min Act: -0.1700
Data Index: 22402 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.0911. Min Act: -0.1700
Data Index: 1339851 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.0911. Min Act: -0.1700
Data Index: 418307 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.1223. Min Act: -0.1700
Data Index: 527872 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.1223. Min Act: -0.1700
Data Index: 1044996 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.1223. Min Act: -0.1700
Data Index: 1034528 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.0598. Min Act: -0.1700
Data Index: 807788 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.1536. Min Act: -0.1700
Data Index: 1202208 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.0598. Min Act: -0.1700
Data Index: 1001711 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6849. Min Range: -4.6849
Max Act: 3.9973. Min Act: -0.1700
Data Index: 1344833 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6849. Min Range: -4.6849
Max Act: 4.0285. Min Act: -0.1700
Data Index: 312174 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19