Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.5618. Min Act: -0.1700
Data Index: 2515963 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.5618. Min Act: -0.1700
Data Index: 6738640 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.5149. Min Act: -0.1700
Data Index: 2168984 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.5149. Min Act: -0.1700
Data Index: 8257362 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4679. Min Act: -0.1700
Data Index: 6311053 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4365. Min Act: -0.1700
Data Index: 353639 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4522. Min Act: -0.1700
Data Index: 7214488 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 1147516 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4052. Min Act: -0.1700
Data Index: 4897089 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4365. Min Act: -0.1700
Data Index: 2987387 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 181795 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 7066551 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 7765731 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4522. Min Act: -0.1700
Data Index: 4874585 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 920943 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 3519419 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4209. Min Act: -0.1700
Data Index: 635347 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4052. Min Act: -0.1700
Data Index: 2143288 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4052. Min Act: -0.1700
Data Index: 8167933 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5618. Min Range: -3.5618
Max Act: 3.4052. Min Act: -0.1700
Data Index: 5273599 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19