Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0871. Min Range: -5.0871
Max Act: 5.0871. Min Act: -0.1700
Data Index: 5078259 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.9934. Min Act: -0.1700
Data Index: 8668991 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.9934. Min Act: -0.1699
Data Index: 1538648 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.9309. Min Act: -0.1700
Data Index: 7614354 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.8684. Min Act: -0.1700
Data Index: 7237817 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.8059. Min Act: -0.1700
Data Index: 3577999 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.8059. Min Act: -0.1700
Data Index: 7148233 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7746. Min Act: -0.1700
Data Index: 8057444 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.8059. Min Act: -0.1700
Data Index: 8081496 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 3235174 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 874947 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.6809. Min Act: -0.1700
Data Index: 127080 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 4053876 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 7286156 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 2169535 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1699
Data Index: 5214467 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 4795269 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.7121. Min Act: -0.1700
Data Index: 7596186 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.6809. Min Act: -0.1700
Data Index: 5040856 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0871. Min Range: -5.0871
Max Act: 4.6809. Min Act: -0.1700
Data Index: 1115550 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19