Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1909 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3976. Min Act: -0.1700
Data Index: 5730777 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3976. Min Act: -0.1700
Data Index: 1858357 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 2478317 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 6087616 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3663. Min Act: -0.1700
Data Index: 256692 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 7326789 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 1766837 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 619380 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 5168529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3663. Min Act: -0.1700
Data Index: 1599235 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 2724602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.3351. Min Act: -0.1700
Data Index: 6629302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.2726. Min Act: -0.1700
Data Index: 2570275 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.2101. Min Act: -0.1700
Data Index: 6661722 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.2413. Min Act: -0.1700
Data Index: 5804407 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.2101. Min Act: -0.1700
Data Index: 4507757 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.1788. Min Act: -0.1700
Data Index: 6764423 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.2101. Min Act: -0.1700
Data Index: 4753321 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.2413. Min Act: -0.1700
Data Index: 4054221 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3976. Min Range: -4.3976
Max Act: 4.1788. Min Act: -0.1700
Data Index: 1214652 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19