Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3098. Min Range: -5.3098
Max Act: 5.3098. Min Act: -0.1700
Data Index: 5436247 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3098. Min Range: -5.3098
Max Act: 5.1536. Min Act: -0.1700
Data Index: 2279026 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3098. Min Range: -5.3098
Max Act: 5.1223. Min Act: -0.1700
Data Index: 4540635 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.9973. Min Act: -0.1700
Data Index: 3898238 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.9348. Min Act: -0.1700
Data Index: 3898239 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.9036. Min Act: -0.1700
Data Index: 2776748 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.9036. Min Act: -0.1700
Data Index: 4540637 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.9036. Min Act: -0.1700
Data Index: 2312088 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.8411. Min Act: -0.1700
Data Index: 2279027 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.8411. Min Act: -0.1700
Data Index: 1241405 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.8098. Min Act: -0.1700
Data Index: 3883335 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.7786. Min Act: -0.1700
Data Index: 5436246 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.7786. Min Act: -0.1700
Data Index: 5027771 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.8098. Min Act: -0.1700
Data Index: 7937670 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.7473. Min Act: -0.1700
Data Index: 114859 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.6848. Min Act: -0.1700
Data Index: 258954 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.7473. Min Act: -0.1700
Data Index: 1243544 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.7161. Min Act: -0.1700
Data Index: 2279024 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.7473. Min Act: -0.1700
Data Index: 1241407 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3098. Min Range: -5.3098
Max Act: 4.6848. Min Act: -0.1700
Data Index: 4907390 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19