Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0755. Min Range: -5.0755
Max Act: 5.0755. Min Act: -0.1700
Data Index: 1500640 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.9505. Min Act: -0.1700
Data Index: 6908207 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.9192. Min Act: -0.1700
Data Index: 1977225 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.8567. Min Act: -0.1700
Data Index: 2513466 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.8567. Min Act: -0.1700
Data Index: 7189129 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7942. Min Act: -0.1700
Data Index: 8286017 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7942. Min Act: -0.1700
Data Index: 4424001 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7630. Min Act: -0.1700
Data Index: 2583065 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7317. Min Act: -0.1700
Data Index: 3329329 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7005. Min Act: -0.1700
Data Index: 6740806 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7005. Min Act: -0.1700
Data Index: 7917143 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6692. Min Act: -0.1700
Data Index: 8490005 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7005. Min Act: -0.1700
Data Index: 6764645 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.7005. Min Act: -0.1700
Data Index: 6296320 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6692. Min Act: -0.1700
Data Index: 4058645 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6380. Min Act: -0.1700
Data Index: 7825821 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6380. Min Act: -0.1700
Data Index: 3938498 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6380. Min Act: -0.1700
Data Index: 8274332 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6380. Min Act: -0.1700
Data Index: 8700044 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0755. Min Range: -5.0755
Max Act: 4.6067. Min Act: -0.1700
Data Index: 1010132 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19