Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1995 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.9282. Min Act: -0.1700
Data Index: 1117760 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.9124. Min Act: -0.1700
Data Index: 1633575 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8330. Min Act: -0.1700
Data Index: 1657002 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8489. Min Act: -0.1700
Data Index: 1418288 (Python Code)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8171. Min Act: -0.1700
Data Index: 1558596 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8012. Min Act: -0.1700
Data Index: 1503881 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8171. Min Act: -0.1700
Data Index: 1440754 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8171. Min Act: -0.1700
Data Index: 1613929 (Python Code)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8012. Min Act: -0.1700
Data Index: 1567100 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8171. Min Act: -0.1700
Data Index: 429440 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7852. Min Act: -0.1700
Data Index: 1608057 (Python Code)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.8171. Min Act: -0.1700
Data Index: 1480235 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7693. Min Act: -0.1700
Data Index: 1559290 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7374. Min Act: -0.1700
Data Index: 1623827 (Python Code)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7533. Min Act: -0.1700
Data Index: 1383439 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7852. Min Act: -0.1700
Data Index: 690836 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7852. Min Act: -0.1700
Data Index: 353130 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7693. Min Act: -0.1700
Data Index: 1577152 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7374. Min Act: -0.1700
Data Index: 1622569 (Python Code)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9282. Min Range: -2.9282
Max Act: 2.7533. Min Act: -0.1700
Data Index: 1451262 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19