Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.6609. Min Act: -0.1700
Data Index: 7063319 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.6435. Min Act: -0.1700
Data Index: 2793197 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.6086. Min Act: -0.1700
Data Index: 1610123 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.6086. Min Act: -0.1700
Data Index: 1947178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5562. Min Act: -0.1700
Data Index: 6293131 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5387. Min Act: -0.1700
Data Index: 1887786 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5211. Min Act: -0.1700
Data Index: 2501065 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5299. Min Act: -0.1700
Data Index: 4533365 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5211. Min Act: -0.1700
Data Index: 3022583 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5299. Min Act: -0.1700
Data Index: 6951802 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5211. Min Act: -0.1700
Data Index: 4795142 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5124. Min Act: -0.1700
Data Index: 5627439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5124. Min Act: -0.1700
Data Index: 3619918 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5036. Min Act: -0.1700
Data Index: 3384513 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.5036. Min Act: -0.1700
Data Index: 8469863 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.4948. Min Act: -0.1700
Data Index: 5939745 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.4948. Min Act: -0.1700
Data Index: 6258693 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.4860. Min Act: -0.1700
Data Index: 677861 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.4948. Min Act: -0.1700
Data Index: 6726957 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6609. Min Range: -1.6609
Max Act: 1.4948. Min Act: -0.1700
Data Index: 7652742 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19