Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0933. Min Range: -6.0933
Max Act: 6.0933. Min Act: -0.1700
Data Index: 4202661 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0933. Min Range: -6.0933
Max Act: 6.0308. Min Act: -0.1700
Data Index: 6620036 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.9996. Min Act: -0.1700
Data Index: 267573 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.9683. Min Act: -0.1700
Data Index: 4958935 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.9371. Min Act: -0.1700
Data Index: 6981721 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3107946 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3223209 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1847451 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8746. Min Act: -0.1700
Data Index: 609365 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8746. Min Act: -0.1700
Data Index: 977737 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8433. Min Act: -0.1700
Data Index: 1423966 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5250829 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 253693 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 2329540 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5512500 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 2783898 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8433. Min Act: -0.1700
Data Index: 7914162 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 4091762 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7808. Min Act: -0.1700
Data Index: 2910217 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7808. Min Act: -0.1700
Data Index: 2220370 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19