Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3913. Min Range: -5.3913
Max Act: 5.3913. Min Act: -0.1700
Data Index: 5661310 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3913. Min Range: -5.3913
Max Act: 5.2976. Min Act: -0.1700
Data Index: 4846014 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.7351. Min Act: -0.1700
Data Index: 300496 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.6726. Min Act: -0.1700
Data Index: 5088331 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.6101. Min Act: -0.1700
Data Index: 422717 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.5788. Min Act: -0.1700
Data Index: 2143124 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.5788. Min Act: -0.1700
Data Index: 4977880 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.5476. Min Act: -0.1700
Data Index: 8297650 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.5163. Min Act: -0.1700
Data Index: 8019360 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4851. Min Act: -0.1700
Data Index: 5413752 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.5163. Min Act: -0.1700
Data Index: 8045373 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4851. Min Act: -0.1700
Data Index: 7885517 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4538. Min Act: -0.1700
Data Index: 1076475 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4851. Min Act: -0.1700
Data Index: 4674657 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.5163. Min Act: -0.1700
Data Index: 5512771 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4851. Min Act: -0.1700
Data Index: 751603 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4851. Min Act: -0.1700
Data Index: 528614 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4538. Min Act: -0.1700
Data Index: 2136075 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4538. Min Act: -0.1700
Data Index: 2383564 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3913. Min Range: -5.3913
Max Act: 4.4538. Min Act: -0.1700
Data Index: 1166237 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19