Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 669 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.3600. Min Act: -0.1700
Data Index: 7533138 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.2975. Min Act: -0.1700
Data Index: 4123061 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.2037. Min Act: -0.1700
Data Index: 7961595 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.1725. Min Act: -0.1700
Data Index: 1816213 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0787. Min Act: -0.1700
Data Index: 1692286 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0474. Min Act: -0.1700
Data Index: 4970222 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0787. Min Act: -0.1700
Data Index: 3509810 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0162. Min Act: -0.1700
Data Index: 3160855 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0474. Min Act: -0.1700
Data Index: 3302772 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0162. Min Act: -0.1700
Data Index: 4008541 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3600. Min Range: -4.3600
Max Act: 4.0162. Min Act: -0.1700
Data Index: 825858 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9849. Min Act: -0.1700
Data Index: 3712044 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9537. Min Act: -0.1700
Data Index: 1503030 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9537. Min Act: -0.1700
Data Index: 3062072 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9537. Min Act: -0.1700
Data Index: 2529941 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9537. Min Act: -0.1700
Data Index: 4149365 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.8911. Min Act: -0.1700
Data Index: 5258615 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9224. Min Act: -0.1700
Data Index: 1931115 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9224. Min Act: -0.1700
Data Index: 5594706 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3600. Min Range: -4.3600
Max Act: 3.9537. Min Act: -0.1700
Data Index: 2622065 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19