Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0720. Min Range: -5.0720
Max Act: 5.0720. Min Act: -0.1700
Data Index: 1523645 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0720. Min Range: -5.0720
Max Act: 5.0095. Min Act: -0.1700
Data Index: 7517439 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0720. Min Range: -5.0720
Max Act: 5.0720. Min Act: -0.1700
Data Index: 1357132 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0720. Min Range: -5.0720
Max Act: 5.0095. Min Act: -0.1700
Data Index: 651503 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0720. Min Range: -5.0720
Max Act: 5.0095. Min Act: -0.1700
Data Index: 2833484 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3312181 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9783. Min Act: -0.1700
Data Index: 683982 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9470. Min Act: -0.1700
Data Index: 3594730 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9470. Min Act: -0.1700
Data Index: 4110260 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9470. Min Act: -0.1700
Data Index: 3226588 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9470. Min Act: -0.1700
Data Index: 2463819 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8845. Min Act: -0.1700
Data Index: 1517348 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9158. Min Act: -0.1700
Data Index: 3505238 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.9158. Min Act: -0.1700
Data Index: 7923899 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8533. Min Act: -0.1700
Data Index: 286282 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8533. Min Act: -0.1700
Data Index: 5760732 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8845. Min Act: -0.1700
Data Index: 2618510 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8845. Min Act: -0.1700
Data Index: 794008 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8220. Min Act: -0.1700
Data Index: 4644318 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0720. Min Range: -5.0720
Max Act: 4.8533. Min Act: -0.1700
Data Index: 5692048 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19