Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.8284. Min Act: -0.1700
Data Index: 4790088 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.7347. Min Act: -0.1700
Data Index: 8008778 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.6409. Min Act: -0.1700
Data Index: 3528526 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.6722. Min Act: -0.1700
Data Index: 4244401 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.5159. Min Act: -0.1700
Data Index: 2629870 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.5159. Min Act: -0.1700
Data Index: 5738247 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 8684246 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.4847. Min Act: -0.1700
Data Index: 2993473 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 2183622 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 909335 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 6753207 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 5423403 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3597. Min Act: -0.1700
Data Index: 1437840 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 4007082 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 5260312 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.2659. Min Act: -0.1700
Data Index: 6992316 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 6248760 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.2972. Min Act: -0.1700
Data Index: 2514831 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 3903624 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 5694034 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19