Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.7136. Min Act: -0.1700
Data Index: 2844137 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.6979. Min Act: -0.1700
Data Index: 4835180 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.6667. Min Act: -0.1700
Data Index: 7542602 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.6667. Min Act: -0.1700
Data Index: 3240374 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.6197. Min Act: -0.1700
Data Index: 295338 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5884. Min Act: -0.1700
Data Index: 2784676 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5884. Min Act: -0.1700
Data Index: 6793761 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5571. Min Act: -0.1700
Data Index: 5515278 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5728. Min Act: -0.1700
Data Index: 1550269 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5571. Min Act: -0.1700
Data Index: 6462521 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5571. Min Act: -0.1700
Data Index: 7011024 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5571. Min Act: -0.1700
Data Index: 567353 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 3184633 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 5056135 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 440120 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5258. Min Act: -0.1700
Data Index: 6793753 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 8324459 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 1074833 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 2312663 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7136. Min Range: -3.7136
Max Act: 3.5415. Min Act: -0.1700
Data Index: 3755194 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19