Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5806 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.6637. Min Act: -0.1700
Data Index: 3622076 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.6012. Min Act: -0.1700
Data Index: 3868139 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.4762. Min Act: -0.1700
Data Index: 5825013 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.5387. Min Act: -0.1700
Data Index: 3762587 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.4762. Min Act: -0.1700
Data Index: 7155622 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.4137. Min Act: -0.1700
Data Index: 7617457 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.3512. Min Act: -0.1700
Data Index: 1432322 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.3512. Min Act: -0.1700
Data Index: 104793 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.2887. Min Act: -0.1700
Data Index: 4878057 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.2262. Min Act: -0.1700
Data Index: 4016751 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.2262. Min Act: -0.1700
Data Index: 4826952 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.2262. Min Act: -0.1700
Data Index: 3011240 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.1637. Min Act: -0.1700
Data Index: 3774640 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.0387. Min Act: -0.1700
Data Index: 4594529 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.1012. Min Act: -0.1700
Data Index: 4238869 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.1012. Min Act: -0.1700
Data Index: 8014381 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.0387. Min Act: -0.1700
Data Index: 6161847 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.0387. Min Act: -0.1700
Data Index: 2775091 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6637. Min Range: -10.6637
Max Act: 10.0387. Min Act: -0.1700
Data Index: 7253849 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6637. Min Range: -10.6637
Max Act: 9.9762. Min Act: -0.1700
Data Index: 8805543 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19