Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.6001. Min Act: -0.1700
Data Index: 1922029 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.4751. Min Act: -0.1700
Data Index: 4012909 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.4126. Min Act: -0.1700
Data Index: 7151156 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.3501. Min Act: -0.1700
Data Index: 3798348 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.3501. Min Act: -0.1700
Data Index: 1234368 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.3501. Min Act: -0.1700
Data Index: 5669777 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.3501. Min Act: -0.1700
Data Index: 1410102 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2875. Min Act: -0.1700
Data Index: 6039833 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2875. Min Act: -0.1700
Data Index: 5812375 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2875. Min Act: -0.1700
Data Index: 3152357 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2563. Min Act: -0.1700
Data Index: 2475303 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2563. Min Act: -0.1700
Data Index: 7124867 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2250. Min Act: -0.1700
Data Index: 7961907 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2250. Min Act: -0.1700
Data Index: 7396355 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2250. Min Act: -0.1700
Data Index: 2727811 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2250. Min Act: -0.1700
Data Index: 8709498 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2563. Min Act: -0.1700
Data Index: 1612377 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.2250. Min Act: -0.1700
Data Index: 3843844 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.1938. Min Act: -0.1700
Data Index: 923877 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6001. Min Range: -4.6001
Max Act: 4.1938. Min Act: -0.1700
Data Index: 950010 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19