Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6339 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4882. Min Range: -6.4882
Max Act: 6.4882. Min Act: -0.1700
Data Index: 2596599 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4882. Min Range: -6.4882
Max Act: 6.0194. Min Act: -0.1700
Data Index: 5650246 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4882. Min Range: -6.4882
Max Act: 6.0194. Min Act: -0.1700
Data Index: 2515190 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.9882. Min Act: -0.1700
Data Index: 2631847 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.9569. Min Act: -0.1700
Data Index: 4277044 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.9569. Min Act: -0.1700
Data Index: 2234733 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.9569. Min Act: -0.1700
Data Index: 8359467 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.9257. Min Act: -0.1700
Data Index: 3351070 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8944. Min Act: -0.1700
Data Index: 7945663 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8632. Min Act: -0.1700
Data Index: 2961993 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8632. Min Act: -0.1700
Data Index: 6193883 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8632. Min Act: -0.1700
Data Index: 1482142 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8632. Min Act: -0.1700
Data Index: 216300 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8319. Min Act: -0.1700
Data Index: 2621023 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8319. Min Act: -0.1700
Data Index: 2704425 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8319. Min Act: -0.1700
Data Index: 5223024 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8319. Min Act: -0.1700
Data Index: 8708659 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8319. Min Act: -0.1700
Data Index: 4511422 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8319. Min Act: -0.1700
Data Index: 6526972 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4882. Min Range: -6.4882
Max Act: 5.8007. Min Act: -0.1700
Data Index: 4725088 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19