Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1603. Min Range: -8.1603
Max Act: 8.1603. Min Act: -0.1700
Data Index: 1770321 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1603. Min Range: -8.1603
Max Act: 8.0978. Min Act: -0.1700
Data Index: 6690224 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.9416. Min Act: -0.1700
Data Index: 6882751 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6916. Min Act: -0.1700
Data Index: 8209853 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6603. Min Act: -0.1700
Data Index: 7172331 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.7228. Min Act: -0.1700
Data Index: 4630955 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6603. Min Act: -0.1700
Data Index: 655418 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6603. Min Act: -0.1700
Data Index: 2328477 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6603. Min Act: -0.1700
Data Index: 3838794 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6291. Min Act: -0.1700
Data Index: 4672375 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6291. Min Act: -0.1700
Data Index: 7374157 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.6291. Min Act: -0.1700
Data Index: 4199676 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.5978. Min Act: -0.1700
Data Index: 7124019 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.5353. Min Act: -0.1700
Data Index: 3430760 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.5353. Min Act: -0.1700
Data Index: 261242 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.4728. Min Act: -0.1700
Data Index: 5823956 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.4728. Min Act: -0.1700
Data Index: 1577867 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.4728. Min Act: -0.1700
Data Index: 6192608 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.4728. Min Act: -0.1700
Data Index: 5344446 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1603. Min Range: -8.1603
Max Act: 7.4416. Min Act: -0.1700
Data Index: 8593254 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19