Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.6939. Min Act: -0.1700
Data Index: 5153634 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.5377. Min Act: -0.1700
Data Index: 2282264 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.3189. Min Act: -0.1700
Data Index: 4933473 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1939. Min Act: -0.1700
Data Index: 7072682 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.2252. Min Act: -0.1700
Data Index: 7745986 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.2252. Min Act: -0.1700
Data Index: 5085202 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1939. Min Act: -0.1700
Data Index: 6668688 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1939. Min Act: -0.1700
Data Index: 7469109 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1939. Min Act: -0.1700
Data Index: 2561381 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3270664 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1627. Min Act: -0.1700
Data Index: 2208886 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3657582 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1314. Min Act: -0.1700
Data Index: 423318 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1002. Min Act: -0.1700
Data Index: 4480438 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1002. Min Act: -0.1700
Data Index: 4022875 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1002. Min Act: -0.1700
Data Index: 7925938 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1314. Min Act: -0.1700
Data Index: 8411351 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1002. Min Act: -0.1700
Data Index: 691422 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.1002. Min Act: -0.1700
Data Index: 1011097 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6939. Min Range: -5.6939
Max Act: 5.0689. Min Act: -0.1700
Data Index: 4409817 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19