Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.7746. Min Act: -0.1700
Data Index: 7342813 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.3059. Min Act: -0.1700
Data Index: 7408424 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0871. Min Act: -0.1700
Data Index: 1646623 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0559. Min Act: -0.1700
Data Index: 8604800 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0559. Min Act: -0.1700
Data Index: 23422 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0559. Min Act: -0.1700
Data Index: 5652418 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0559. Min Act: -0.1700
Data Index: 35328 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0559. Min Act: -0.1700
Data Index: 7134118 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 5312059 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 1359935 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0246. Min Act: -0.1700
Data Index: 4277752 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 2517729 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0246. Min Act: -0.1700
Data Index: 22946 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0246. Min Act: -0.1700
Data Index: 4000840 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 6348798 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 2952297 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0246. Min Act: -0.1700
Data Index: 4023285 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 3735596 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7746. Min Range: -5.7746
Max Act: 4.9934. Min Act: -0.1700
Data Index: 6773981 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7746. Min Range: -5.7746
Max Act: 5.0246. Min Act: -0.1700
Data Index: 2701805 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19