Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 98 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.5586. Min Act: -0.1700
Data Index: 799129 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.5263. Min Act: -0.1700
Data Index: 281623 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.5101. Min Act: -0.1700
Data Index: 1547668 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4939. Min Act: -0.1700
Data Index: 1453006 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4777. Min Act: -0.1700
Data Index: 1164748 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4615. Min Act: -0.1700
Data Index: 1477336 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4777. Min Act: -0.1700
Data Index: 1440479 (Python Code)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4777. Min Act: -0.1700
Data Index: 1448848 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4452. Min Act: -0.1700
Data Index: 1137421 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4290. Min Act: -0.1700
Data Index: 1650477 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4452. Min Act: -0.1700
Data Index: 1457747 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4290. Min Act: -0.1700
Data Index: 1528810 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4452. Min Act: -0.1700
Data Index: 1582691 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4290. Min Act: -0.1700
Data Index: 385126 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4290. Min Act: -0.1700
Data Index: 1498531 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4127. Min Act: -0.1700
Data Index: 1375206 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.3964. Min Act: -0.1700
Data Index: 1450340 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4127. Min Act: -0.1700
Data Index: 1536632 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.4127. Min Act: -0.1700
Data Index: 1317419 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5586. Min Range: -2.5586
Max Act: 2.3964. Min Act: -0.1700
Data Index: 252152 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19