Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4665 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.1860. Min Act: -0.1700
Data Index: 7056920 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.1548. Min Act: -0.1700
Data Index: 2246151 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.0610. Min Act: -0.1700
Data Index: 1019079 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.0923. Min Act: -0.1700
Data Index: 7605809 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.0610. Min Act: -0.1700
Data Index: 1572909 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.0610. Min Act: -0.1700
Data Index: 250529 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.0298. Min Act: -0.1700
Data Index: 8282951 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1860. Min Range: -5.1860
Max Act: 5.0298. Min Act: -0.1700
Data Index: 2164927 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9673. Min Act: -0.1700
Data Index: 8659044 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9985. Min Act: -0.1700
Data Index: 3357082 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9673. Min Act: -0.1700
Data Index: 3864477 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9048. Min Act: -0.1700
Data Index: 7969802 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9360. Min Act: -0.1700
Data Index: 6837773 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9673. Min Act: -0.1700
Data Index: 5203704 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.8735. Min Act: -0.1700
Data Index: 163304 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.9048. Min Act: -0.1700
Data Index: 4923691 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.8735. Min Act: -0.1700
Data Index: 3889173 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.8735. Min Act: -0.1700
Data Index: 1911204 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.8735. Min Act: -0.1700
Data Index: 2483683 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1860. Min Range: -5.1860
Max Act: 4.8735. Min Act: -0.1700
Data Index: 2359112 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19