Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 772 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0604. Min Range: -3.0604
Max Act: 3.0604. Min Act: -0.1700
Data Index: 1362844 (Python Code)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0604. Min Range: -3.0604
Max Act: 3.0288. Min Act: -0.1700
Data Index: 1121912 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0604. Min Range: -3.0604
Max Act: 3.0288. Min Act: -0.1700
Data Index: 1551409 (Python Code)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0604. Min Range: -3.0604
Max Act: 3.0130. Min Act: -0.1700
Data Index: 1415752 (Python Code)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0604. Min Range: -3.0604
Max Act: 3.0130. Min Act: -0.1700
Data Index: 1453700 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9814. Min Act: -0.1700
Data Index: 1137949 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9972. Min Act: -0.1700
Data Index: 1528108 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9972. Min Act: -0.1700
Data Index: 1458435 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9972. Min Act: -0.1700
Data Index: 781904 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9814. Min Act: -0.1700
Data Index: 1460111 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9972. Min Act: -0.1700
Data Index: 1056446 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9814. Min Act: -0.1700
Data Index: 775697 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9656. Min Act: -0.1700
Data Index: 136978 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9497. Min Act: -0.1700
Data Index: 589244 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9339. Min Act: -0.1700
Data Index: 1360218 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9497. Min Act: -0.1700
Data Index: 1420237 (Python Code)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9339. Min Act: -0.1700
Data Index: 1409949 (Python Code)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9497. Min Act: -0.1700
Data Index: 1550260 (Python Code)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9497. Min Act: -0.1700
Data Index: 1616661 (Python Code)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0604. Min Range: -3.0604
Max Act: 2.9497. Min Act: -0.1700
Data Index: 1566631 (Python Code)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19