Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2206 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.7819. Min Act: -0.1700
Data Index: 5184191 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6881. Min Act: -0.1700
Data Index: 4204530 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6725. Min Act: -0.1700
Data Index: 1863116 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6568. Min Act: -0.1700
Data Index: 3850055 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6412. Min Act: -0.1700
Data Index: 7151714 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6568. Min Act: -0.1700
Data Index: 4233554 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6568. Min Act: -0.1700
Data Index: 4790476 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6412. Min Act: -0.1700
Data Index: 1841605 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6255. Min Act: -0.1700
Data Index: 1499289 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6255. Min Act: -0.1700
Data Index: 5414149 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6255. Min Act: -0.1700
Data Index: 7882369 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6099. Min Act: -0.1700
Data Index: 3093145 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6099. Min Act: -0.1700
Data Index: 5574372 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6099. Min Act: -0.1700
Data Index: 4448020 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6099. Min Act: -0.1700
Data Index: 7793715 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.5786. Min Act: -0.1700
Data Index: 5510776 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.6099. Min Act: -0.1700
Data Index: 2432626 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.5629. Min Act: -0.1700
Data Index: 1236657 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.5942. Min Act: -0.1700
Data Index: 4732752 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7819. Min Range: -3.7819
Max Act: 3.5942. Min Act: -0.1700
Data Index: 1543070 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19