Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.5086. Min Act: -0.1700
Data Index: 4451514 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.5711. Min Act: -0.1700
Data Index: 7368478 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4773. Min Act: -0.1700
Data Index: 4361955 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4148. Min Act: -0.1700
Data Index: 4361954 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4148. Min Act: -0.1700
Data Index: 7620244 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4461. Min Act: -0.1700
Data Index: 543071 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4148. Min Act: -0.1700
Data Index: 6929694 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4148. Min Act: -0.1700
Data Index: 2635025 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.4461. Min Act: -0.1700
Data Index: 5955358 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3836. Min Act: -0.1700
Data Index: 2486502 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3523. Min Act: -0.1700
Data Index: 1837303 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3836. Min Act: -0.1700
Data Index: 4361959 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3523. Min Act: -0.1700
Data Index: 796333 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3523. Min Act: -0.1700
Data Index: 1391124 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3836. Min Act: -0.1700
Data Index: 568630 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3523. Min Act: -0.1700
Data Index: 2313535 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3211. Min Act: -0.1700
Data Index: 3690858 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3523. Min Act: -0.1700
Data Index: 7275263 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3211. Min Act: -0.1700
Data Index: 2206356 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5711. Min Range: -4.5711
Max Act: 4.3211. Min Act: -0.1700
Data Index: 6270856 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19