Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.5597. Min Act: -0.1700
Data Index: 1062722 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4972. Min Act: -0.1700
Data Index: 5805862 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4659. Min Act: -0.1700
Data Index: 4927703 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4659. Min Act: -0.1700
Data Index: 7183117 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4659. Min Act: -0.1700
Data Index: 7274675 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4347. Min Act: -0.1700
Data Index: 4441740 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4034. Min Act: -0.1700
Data Index: 4843276 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3722. Min Act: -0.1700
Data Index: 5738766 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1247347 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4034. Min Act: -0.1700
Data Index: 926341 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4034. Min Act: -0.1700
Data Index: 750847 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4034. Min Act: -0.1700
Data Index: 253608 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3722. Min Act: -0.1700
Data Index: 8557269 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3722. Min Act: -0.1700
Data Index: 2392157 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1770799 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3409. Min Act: -0.1700
Data Index: 7168222 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3409. Min Act: -0.1700
Data Index: 5053019 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3722. Min Act: -0.1700
Data Index: 2759190 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3097. Min Act: -0.1700
Data Index: 2359817 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5597. Min Range: -4.5597
Max Act: 4.3409. Min Act: -0.1700
Data Index: 5729013 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19