Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4989 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0181. Min Range: -5.0181
Max Act: 5.0181. Min Act: -0.1700
Data Index: 6693025 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8931. Min Act: -0.1700
Data Index: 7643571 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8619. Min Act: -0.1700
Data Index: 6671932 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8619. Min Act: -0.1700
Data Index: 7764752 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8306. Min Act: -0.1700
Data Index: 7687722 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8306. Min Act: -0.1700
Data Index: 8012966 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8306. Min Act: -0.1700
Data Index: 338350 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 3998378 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7994. Min Act: -0.1700
Data Index: 4337005 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7994. Min Act: -0.1700
Data Index: 5033632 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.8306. Min Act: -0.1700
Data Index: 2292619 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7369. Min Act: -0.1700
Data Index: 6671933 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 318404 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7369. Min Act: -0.1700
Data Index: 846750 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 8503059 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 6039697 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 6477439 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 4386503 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 128203 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0181. Min Range: -5.0181
Max Act: 4.7681. Min Act: -0.1700
Data Index: 803404 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19