Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1097 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.8537. Min Act: -0.1700
Data Index: 1205471 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.8537. Min Act: -0.1700
Data Index: 734361 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.7600. Min Act: -0.1700
Data Index: 1100229 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.7287. Min Act: -0.1699
Data Index: 800712 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6975. Min Act: -0.1700
Data Index: 943489 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6975. Min Act: -0.1700
Data Index: 399304 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6662. Min Act: -0.1700
Data Index: 70740 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6350. Min Act: -0.1700
Data Index: 163451 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6037. Min Act: -0.1700
Data Index: 102682 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6662. Min Act: -0.1700
Data Index: 142231 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6037. Min Act: -0.1700
Data Index: 515057 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6350. Min Act: -0.1700
Data Index: 60962 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.5725. Min Act: -0.1700
Data Index: 846520 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.5725. Min Act: -0.1700
Data Index: 572249 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.5725. Min Act: -0.1700
Data Index: 1279253 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.6037. Min Act: -0.1700
Data Index: 314514 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.5412. Min Act: -0.1700
Data Index: 13 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.5412. Min Act: -0.1700
Data Index: 592517 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.5725. Min Act: -0.1700
Data Index: 501215 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8537. Min Range: -4.8537
Max Act: 4.4787. Min Act: -0.1700
Data Index: 1002778 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19