Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3229 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.2560. Min Act: -0.1700
Data Index: 561399 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.1935. Min Act: -0.1700
Data Index: 1744724 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2560. Min Range: -6.2560
Max Act: 6.1310. Min Act: -0.1700
Data Index: 795587 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.6935. Min Act: -0.1700
Data Index: 3939532 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3810. Min Act: -0.1700
Data Index: 4034062 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3498. Min Act: -0.1700
Data Index: 1234585 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3185. Min Act: -0.1700
Data Index: 4902977 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3498. Min Act: -0.1700
Data Index: 795588 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3498. Min Act: -0.1700
Data Index: 5933248 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3185. Min Act: -0.1700
Data Index: 2872508 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3185. Min Act: -0.1700
Data Index: 1980049 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.3185. Min Act: -0.1700
Data Index: 6168364 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.2560. Min Act: -0.1700
Data Index: 8170001 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.2560. Min Act: -0.1700
Data Index: 2877022 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.2248. Min Act: -0.1700
Data Index: 8827693 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.2248. Min Act: -0.1700
Data Index: 1285125 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.2248. Min Act: -0.1700
Data Index: 7584044 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.2248. Min Act: -0.1700
Data Index: 6205950 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.1935. Min Act: -0.1700
Data Index: 44272 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2560. Min Range: -6.2560
Max Act: 5.1935. Min Act: -0.1700
Data Index: 515325 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19