Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 249 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7574. Min Act: -0.1700
Data Index: 6214758 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7315. Min Act: -0.1700
Data Index: 4407697 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7315. Min Act: -0.1681
Data Index: 1202104 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7315. Min Act: -0.1700
Data Index: 1177507 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7142. Min Act: -0.1700
Data Index: 3086269 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7142. Min Act: -0.1700
Data Index: 4198595 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7142. Min Act: -0.1700
Data Index: 3969331 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7055. Min Act: -0.1700
Data Index: 2360850 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7055. Min Act: -0.1700
Data Index: 2680338 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7142. Min Act: -0.1700
Data Index: 8413796 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7055. Min Act: -0.1700
Data Index: 7616605 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7142. Min Act: -0.1699
Data Index: 3195487 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.7055. Min Act: -0.1700
Data Index: 4829322 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6969. Min Act: -0.1700
Data Index: 7025080 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6795. Min Act: -0.1700
Data Index: 2480722 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6795. Min Act: -0.1700
Data Index: 3016296 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6882. Min Act: -0.1700
Data Index: 3324982 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6795. Min Act: -0.1700
Data Index: 6312829 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6969. Min Act: -0.1700
Data Index: 445685 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7574. Min Range: -1.7574
Max Act: 1.6795. Min Act: -0.1700
Data Index: 1029666 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19