Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 567 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.0221. Min Range: -5.0221
Max Act: 5.0221. Min Act: -0.1700
Data Index: 564240 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.7252. Min Act: -0.1700
Data Index: 160668 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.6939. Min Act: -0.1700
Data Index: 1000743 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.6627. Min Act: -0.1700
Data Index: 248202 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.6627. Min Act: -0.1700
Data Index: 1026138 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.6314. Min Act: -0.1700
Data Index: 1175320 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.5689. Min Act: -0.1700
Data Index: 20263 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.5533. Min Act: -0.1700
Data Index: 1126061 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.5845. Min Act: -0.1700
Data Index: 573927 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.5064. Min Act: -0.1700
Data Index: 80166 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4908. Min Act: -0.1700
Data Index: 959396 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.5689. Min Act: -0.1700
Data Index: 337973 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.5533. Min Act: -0.1700
Data Index: 177007 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4908. Min Act: -0.1700
Data Index: 487766 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4908. Min Act: -0.1700
Data Index: 245963 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4752. Min Act: -0.1700
Data Index: 377862 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4439. Min Act: -0.1700
Data Index: 551831 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4908. Min Act: -0.1700
Data Index: 220458 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4595. Min Act: -0.1700
Data Index: 797912 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0221. Min Range: -5.0221
Max Act: 4.4439. Min Act: -0.1700
Data Index: 455487 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19