Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 481 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0142. Min Range: -5.0142
Max Act: 5.0142. Min Act: -0.1700
Data Index: 523458 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0142. Min Range: -5.0142
Max Act: 5.0142. Min Act: -0.1700
Data Index: 5314146 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0142. Min Range: -5.0142
Max Act: 5.0142. Min Act: -0.1700
Data Index: 7105662 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.9829. Min Act: -0.1700
Data Index: 2867727 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.9829. Min Act: -0.1700
Data Index: 5314148 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.9204. Min Act: -0.1700
Data Index: 5314147 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.9204. Min Act: -0.1700
Data Index: 2867724 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.9204. Min Act: -0.1700
Data Index: 4554505 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 523436 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 523446 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 4225619 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 523452 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 3887973 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 523432 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 5314132 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.9204. Min Act: -0.1700
Data Index: 5314125 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8579. Min Act: -0.1700
Data Index: 523425 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 1270670 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8579. Min Act: -0.1700
Data Index: 5314130 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0142. Min Range: -5.0142
Max Act: 4.8891. Min Act: -0.1700
Data Index: 5314139 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19