Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 213 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1102. Min Range: -5.1102
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6488676 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9852. Min Act: -0.1700
Data Index: 8023784 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9852. Min Act: -0.1700
Data Index: 3660953 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9540. Min Act: -0.1700
Data Index: 4063059 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9227. Min Act: -0.1700
Data Index: 6493800 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9227. Min Act: -0.1700
Data Index: 3419521 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 897433 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 2464574 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 2946559 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 3949796 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 1477472 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 3368135 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 3669447 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 2786866 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4482212 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8290. Min Act: -0.1700
Data Index: 2865552 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8290. Min Act: -0.1700
Data Index: 5437032 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 4998782 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4775952 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.7977. Min Act: -0.1700
Data Index: 2785226 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19