Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.6835. Min Act: -0.1700
Data Index: 6920947 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.6210. Min Act: -0.1700
Data Index: 6864573 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.6210. Min Act: -0.1695
Data Index: 8645684 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5898. Min Act: -0.1699
Data Index: 5436211 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5898. Min Act: -0.1697
Data Index: 4551517 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5585. Min Act: -0.1694
Data Index: 7824466 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5585. Min Act: -0.1700
Data Index: 4681115 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5585. Min Act: -0.1700
Data Index: 6728628 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5273. Min Act: -0.1700
Data Index: 1953778 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5273. Min Act: -0.1700
Data Index: 8292033 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5273. Min Act: -0.1700
Data Index: 356036 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.5273. Min Act: -0.1700
Data Index: 6562243 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4960. Min Act: -0.1700
Data Index: 900441 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4960. Min Act: -0.1700
Data Index: 7299342 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4960. Min Act: -0.1700
Data Index: 6062408 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4648. Min Act: -0.1700
Data Index: 8404516 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4648. Min Act: -0.1700
Data Index: 3189665 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4648. Min Act: -0.1698
Data Index: 4810417 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4335. Min Act: -0.1700
Data Index: 863864 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6835. Min Range: -4.6835
Max Act: 4.4648. Min Act: -0.1687
Data Index: 4931182 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19