Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.3982. Min Act: -0.1700
Data Index: 7475989 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0232. Min Act: -0.1700
Data Index: 2135651 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9919. Min Act: -0.1700
Data Index: 295175 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9919. Min Act: -0.1700
Data Index: 1389802 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9607. Min Act: -0.1700
Data Index: 1240313 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9607. Min Act: -0.1700
Data Index: 3624955 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9294. Min Act: -0.1700
Data Index: 4480461 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9607. Min Act: -0.1700
Data Index: 5169544 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9294. Min Act: -0.1700
Data Index: 5917290 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 7595931 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9294. Min Act: -0.1700
Data Index: 2731564 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 3970126 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 5468167 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 4442428 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 8272296 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 1812169 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8669. Min Act: -0.1700
Data Index: 732996 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8669. Min Act: -0.1700
Data Index: 166647 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 95653 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.8982. Min Act: -0.1700
Data Index: 166648 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19