Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1376 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0136. Min Range: -4.0136
Max Act: 4.0136. Min Act: -0.1700
Data Index: 947387 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.9198. Min Act: -0.1700
Data Index: 451305 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.9198. Min Act: -0.1700
Data Index: 119240 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.8886. Min Act: -0.1700
Data Index: 591274 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.8260. Min Act: -0.1700
Data Index: 1531911 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.8260. Min Act: -0.1700
Data Index: 1316291 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7947. Min Act: -0.1700
Data Index: 920256 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7947. Min Act: -0.1700
Data Index: 404997 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7321. Min Act: -0.1700
Data Index: 892978 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7478. Min Act: -0.1700
Data Index: 1465116 (Python Code)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7009. Min Act: -0.1700
Data Index: 1474281 (Python Code)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7165. Min Act: -0.1700
Data Index: 1614203 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7478. Min Act: -0.1700
Data Index: 1436616 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7165. Min Act: -0.1700
Data Index: 1536439 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7634. Min Act: -0.1700
Data Index: 862393 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7478. Min Act: -0.1700
Data Index: 1029395 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7321. Min Act: -0.1700
Data Index: 243955 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7009. Min Act: -0.1700
Data Index: 886776 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7009. Min Act: -0.1700
Data Index: 1514727 (Python Code)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0136. Min Range: -4.0136
Max Act: 3.7165. Min Act: -0.1700
Data Index: 1602231 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19