Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.4969. Min Act: -0.1700
Data Index: 8243458 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.3407. Min Act: -0.1700
Data Index: 3169716 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.3094. Min Act: -0.1700
Data Index: 4603653 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.2782. Min Act: -0.1700
Data Index: 4925833 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.2157. Min Act: -0.1700
Data Index: 6418392 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.1844. Min Act: -0.1700
Data Index: 7155789 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.1532. Min Act: -0.1700
Data Index: 496552 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.1219. Min Act: -0.1700
Data Index: 426619 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.1219. Min Act: -0.1700
Data Index: 720187 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.1219. Min Act: -0.1700
Data Index: 8249182 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0594. Min Act: -0.1700
Data Index: 5784031 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0907. Min Act: -0.1700
Data Index: 8531557 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0907. Min Act: -0.1700
Data Index: 2281249 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0907. Min Act: -0.1700
Data Index: 2977463 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0907. Min Act: -0.1700
Data Index: 5979440 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0594. Min Act: -0.1700
Data Index: 8435338 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0594. Min Act: -0.1700
Data Index: 4452957 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0594. Min Act: -0.1700
Data Index: 4246921 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0282. Min Act: -0.1700
Data Index: 4255324 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4969. Min Range: -7.4969
Max Act: 7.0594. Min Act: -0.1700
Data Index: 8117543 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19