Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.9521. Min Act: -0.1700
Data Index: 7710412 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.7019. Min Act: -0.1700
Data Index: 3067036 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.6706. Min Act: -0.1700
Data Index: 568089 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.5924. Min Act: -0.1700
Data Index: 2079829 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.5924. Min Act: -0.1700
Data Index: 2259251 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.5141. Min Act: -0.1700
Data Index: 4359925 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.5141. Min Act: -0.1700
Data Index: 8766167 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.4671. Min Act: -0.1700
Data Index: 4655317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.4828. Min Act: -0.1700
Data Index: 3085123 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7827876 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.4201. Min Act: -0.1700
Data Index: 4895835 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3731. Min Act: -0.1700
Data Index: 7134823 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3417. Min Act: -0.1700
Data Index: 6808240 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3417. Min Act: -0.1700
Data Index: 8157133 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3260. Min Act: -0.1700
Data Index: 7018014 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3417. Min Act: -0.1700
Data Index: 1901621 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3260. Min Act: -0.1700
Data Index: 3282035 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3260. Min Act: -0.1700
Data Index: 6707345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3417. Min Act: -0.1700
Data Index: 5814592 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9521. Min Range: -3.9521
Max Act: 3.3417. Min Act: -0.1700
Data Index: 1477990 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19