Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7201. Min Range: -8.7201
Max Act: 8.7201. Min Act: -0.1700
Data Index: 5650894 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7201. Min Range: -8.7201
Max Act: 8.0326. Min Act: -0.1700
Data Index: 956901 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.9701. Min Act: -0.1700
Data Index: 3428003 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.9701. Min Act: -0.1700
Data Index: 5875885 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.9701. Min Act: -0.1700
Data Index: 2532682 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.9076. Min Act: -0.1700
Data Index: 7235414 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.8451. Min Act: -0.1700
Data Index: 7407195 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.7514. Min Act: -0.1700
Data Index: 1916360 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.7514. Min Act: -0.1700
Data Index: 3192175 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.7201. Min Act: -0.1700
Data Index: 6229265 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.6576. Min Act: -0.1700
Data Index: 6882487 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.6576. Min Act: -0.1700
Data Index: 1028168 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.6264. Min Act: -0.1700
Data Index: 8135712 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5951. Min Act: -0.1700
Data Index: 734003 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5639. Min Act: -0.1700
Data Index: 3644504 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5951. Min Act: -0.1700
Data Index: 4864781 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5326. Min Act: -0.1700
Data Index: 4664447 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5014. Min Act: -0.1700
Data Index: 5693006 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5014. Min Act: -0.1700
Data Index: 1078369 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7201. Min Range: -8.7201
Max Act: 7.5014. Min Act: -0.1700
Data Index: 770328 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19