Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.4265. Min Act: -0.1700
Data Index: 2168839 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.3015. Min Act: -0.1700
Data Index: 27886 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.3015. Min Act: -0.1700
Data Index: 6056078 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.2390. Min Act: -0.1700
Data Index: 2415944 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.1765. Min Act: -0.1700
Data Index: 6218301 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.2077. Min Act: -0.1700
Data Index: 6214655 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.1452. Min Act: -0.1700
Data Index: 5687467 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.0515. Min Act: -0.1700
Data Index: 5286352 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4265. Min Range: -6.4265
Max Act: 6.0515. Min Act: -0.1700
Data Index: 8321930 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.9577. Min Act: -0.1700
Data Index: 4728280 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.9577. Min Act: -0.1700
Data Index: 7638521 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.9265. Min Act: -0.1700
Data Index: 1974755 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8952. Min Act: -0.1700
Data Index: 8569472 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3032612 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8640. Min Act: -0.1700
Data Index: 6555110 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.9265. Min Act: -0.1700
Data Index: 5414920 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8952. Min Act: -0.1700
Data Index: 241277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8640. Min Act: -0.1700
Data Index: 2597433 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8640. Min Act: -0.1700
Data Index: 4949857 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4265. Min Range: -6.4265
Max Act: 5.8640. Min Act: -0.1700
Data Index: 83665 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19