Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1700 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.6592. Min Act: -0.1700
Data Index: 119811 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.6592. Min Act: -0.1700
Data Index: 1153343 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.6592. Min Act: -0.1700
Data Index: 1123246 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5342. Min Act: -0.1700
Data Index: 272728 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5655. Min Act: -0.1700
Data Index: 406025 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5967. Min Act: -0.1700
Data Index: 1215784 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5655. Min Act: -0.1700
Data Index: 971506 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5655. Min Act: -0.1700
Data Index: 373191 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1183586 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5342. Min Act: -0.1700
Data Index: 207997 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 743544 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1302143 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 636267 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5342. Min Act: -0.1700
Data Index: 1194665 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1200059 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1336111 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1284462 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.4717. Min Act: -0.1700
Data Index: 981087 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.4717. Min Act: -0.1700
Data Index: 583528 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6592. Min Range: -4.6592
Max Act: 4.4405. Min Act: -0.1700
Data Index: 273346 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19