Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1637 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.8099. Min Act: -0.1700
Data Index: 5555840 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.7786. Min Act: -0.1700
Data Index: 3867204 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.7786. Min Act: -0.1700
Data Index: 2180518 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.7161. Min Act: -0.1700
Data Index: 2816383 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6849. Min Act: -0.1700
Data Index: 1574993 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6849. Min Act: -0.1700
Data Index: 7164943 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6849. Min Act: -0.1700
Data Index: 7927907 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6849. Min Act: -0.1700
Data Index: 5555843 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6224. Min Act: -0.1700
Data Index: 3397845 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6536. Min Act: -0.1700
Data Index: 7164942 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6536. Min Act: -0.1700
Data Index: 3969210 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6536. Min Act: -0.1700
Data Index: 347852 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6536. Min Act: -0.1700
Data Index: 157917 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6224. Min Act: -0.1700
Data Index: 3412248 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6224. Min Act: -0.1700
Data Index: 5910759 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6224. Min Act: -0.1700
Data Index: 7934335 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6224. Min Act: -0.1700
Data Index: 602218 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.6224. Min Act: -0.1700
Data Index: 6871516 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.5911. Min Act: -0.1700
Data Index: 5810671 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8099. Min Range: -4.8099
Max Act: 4.5911. Min Act: -0.1700
Data Index: 4775227 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19