Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1938 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0217. Min Range: -3.0217
Max Act: 3.0217. Min Act: -0.1700
Data Index: 125402 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.8634. Min Act: -0.1700
Data Index: 1138400 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7997. Min Act: -0.1700
Data Index: 824238 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7997. Min Act: -0.1700
Data Index: 1322102 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7997. Min Act: -0.1700
Data Index: 159096 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7997. Min Act: -0.1700
Data Index: 774223 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7679. Min Act: -0.1700
Data Index: 649733 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7679. Min Act: -0.1700
Data Index: 961443 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7838. Min Act: -0.1700
Data Index: 290113 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7679. Min Act: -0.1700
Data Index: 578896 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7519. Min Act: -0.1700
Data Index: 1091404 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7519. Min Act: -0.1700
Data Index: 829198 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7679. Min Act: -0.1700
Data Index: 1189129 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7359. Min Act: -0.1700
Data Index: 800801 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7359. Min Act: -0.1700
Data Index: 27977 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7359. Min Act: -0.1700
Data Index: 588693 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7519. Min Act: -0.1700
Data Index: 863962 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7359. Min Act: -0.1700
Data Index: 698698 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7359. Min Act: -0.1700
Data Index: 770067 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0217. Min Range: -3.0217
Max Act: 2.7359. Min Act: -0.1700
Data Index: 892202 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19