Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9044. Min Range: -8.9044
Max Act: 8.9044. Min Act: -0.1700
Data Index: 662611 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.7794. Min Act: -0.1700
Data Index: 8455184 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.5919. Min Act: -0.1700
Data Index: 8408269 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.5294. Min Act: -0.1700
Data Index: 5914512 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.4669. Min Act: -0.1700
Data Index: 5914513 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.3419. Min Act: -0.1700
Data Index: 5914511 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.0919. Min Act: -0.1700
Data Index: 6454323 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.0606. Min Act: -0.1700
Data Index: 6269013 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9044. Min Range: -8.9044
Max Act: 7.0606. Min Act: -0.1700
Data Index: 5124729 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.9981. Min Act: -0.1700
Data Index: 956669 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.9981. Min Act: -0.1699
Data Index: 5067027 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.9669. Min Act: -0.1700
Data Index: 6620013 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.9669. Min Act: -0.1700
Data Index: 7332106 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.9044. Min Act: -0.1700
Data Index: 2812106 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.8419. Min Act: -0.1700
Data Index: 8408270 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.9044. Min Act: -0.1700
Data Index: 7849554 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.8106. Min Act: -0.1700
Data Index: 1895467 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.8106. Min Act: -0.1700
Data Index: 7876033 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.8419. Min Act: -0.1695
Data Index: 2907406 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9044. Min Range: -8.9044
Max Act: 6.8419. Min Act: -0.1700
Data Index: 1509793 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19