Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1695 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.8858. Min Act: -0.1700
Data Index: 1521668 (Python Code)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.6515. Min Act: -0.1700
Data Index: 141051 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.6515. Min Act: -0.1700
Data Index: 601939 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5890. Min Act: -0.1700
Data Index: 1501439 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5733. Min Act: -0.1700
Data Index: 931824 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5421. Min Act: -0.1700
Data Index: 1524496 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5733. Min Act: -0.1700
Data Index: 726373 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5733. Min Act: -0.1700
Data Index: 169201 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5421. Min Act: -0.1700
Data Index: 597601 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5265. Min Act: -0.1700
Data Index: 746161 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.6046. Min Act: -0.1700
Data Index: 959223 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5265. Min Act: -0.1700
Data Index: 383536 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5108. Min Act: -0.1700
Data Index: 1606512 (Python Code)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5733. Min Act: -0.1700
Data Index: 1445782 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5265. Min Act: -0.1700
Data Index: 206115 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.5108. Min Act: -0.1700
Data Index: 1098058 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.4952. Min Act: -0.1700
Data Index: 413847 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.4952. Min Act: -0.1700
Data Index: 1063353 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.4640. Min Act: -0.1700
Data Index: 1513604 (Python Code)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8858. Min Range: -4.8858
Max Act: 4.4171. Min Act: -0.1700
Data Index: 1024527 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19