Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2313 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6855. Min Act: -0.1700
Data Index: 4721423 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6855. Min Act: -0.1700
Data Index: 3219479 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.7167. Min Act: -0.1700
Data Index: 1528774 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6230. Min Act: -0.1700
Data Index: 3262578 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6855. Min Act: -0.1700
Data Index: 2586373 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6855. Min Act: -0.1700
Data Index: 7570600 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6230. Min Act: -0.1700
Data Index: 3402080 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.6542. Min Act: -0.1700
Data Index: 6738074 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.5605. Min Act: -0.1700
Data Index: 6504310 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.5917. Min Act: -0.1700
Data Index: 6651787 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.5292. Min Act: -0.1700
Data Index: 424999 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4355. Min Act: -0.1700
Data Index: 2097010 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4667. Min Act: -0.1700
Data Index: 4817759 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.5605. Min Act: -0.1700
Data Index: 2743539 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4980. Min Act: -0.1700
Data Index: 5338740 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.5292. Min Act: -0.1700
Data Index: 2370994 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4667. Min Act: -0.1700
Data Index: 610024 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4355. Min Act: -0.1700
Data Index: 5313762 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4355. Min Act: -0.1700
Data Index: 5178852 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7167. Min Range: -6.7167
Max Act: 6.4042. Min Act: -0.1700
Data Index: 1073159 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19