Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4404 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.7499. Min Act: -0.1700
Data Index: 3686371 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.6874. Min Act: -0.1700
Data Index: 530447 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.6249. Min Act: -0.1700
Data Index: 3959784 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.6562. Min Act: -0.1700
Data Index: 6689341 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.6249. Min Act: -0.1700
Data Index: 8439060 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5624. Min Act: -0.1700
Data Index: 335730 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5937. Min Act: -0.1700
Data Index: 6907962 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5624. Min Act: -0.1700
Data Index: 5752099 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5624. Min Act: -0.1700
Data Index: 5213625 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5312. Min Act: -0.1700
Data Index: 2999731 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5624. Min Act: -0.1700
Data Index: 6415333 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4999. Min Act: -0.1700
Data Index: 7078905 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4999. Min Act: -0.1700
Data Index: 7893533 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6264788 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4999. Min Act: -0.1700
Data Index: 7789187 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.5312. Min Act: -0.1700
Data Index: 7774746 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6235032 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4999. Min Act: -0.1700
Data Index: 3176862 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4687. Min Act: -0.1700
Data Index: 6721570 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7499. Min Range: -6.7499
Max Act: 6.4374. Min Act: -0.1700
Data Index: 526393 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19