Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5715. Min Range: -10.5715
Max Act: 10.5715. Min Act: -0.1700
Data Index: 268326 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5715. Min Range: -10.5715
Max Act: 10.1965. Min Act: -0.1700
Data Index: 7999265 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5715. Min Range: -10.5715
Max Act: 10.1340. Min Act: -0.1700
Data Index: 7870962 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5715. Min Range: -10.5715
Max Act: 10.0715. Min Act: -0.1700
Data Index: 984815 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5715. Min Range: -10.5715
Max Act: 10.0090. Min Act: -0.1700
Data Index: 2642137 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.9465. Min Act: -0.1700
Data Index: 5963429 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8840. Min Act: -0.1700
Data Index: 2448936 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8840. Min Act: -0.1700
Data Index: 4650259 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8840. Min Act: -0.1700
Data Index: 203092 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8840. Min Act: -0.1700
Data Index: 5618320 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8215. Min Act: -0.1700
Data Index: 1702340 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8215. Min Act: -0.1700
Data Index: 6535650 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.8215. Min Act: -0.1700
Data Index: 3102827 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.7590. Min Act: -0.1700
Data Index: 5547203 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.6965. Min Act: -0.1700
Data Index: 5007088 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.6965. Min Act: -0.1700
Data Index: 4488625 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.6965. Min Act: -0.1700
Data Index: 3176631 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.6965. Min Act: -0.1700
Data Index: 3812196 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.6965. Min Act: -0.1700
Data Index: 7942679 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5715. Min Range: -10.5715
Max Act: 9.6340. Min Act: -0.1700
Data Index: 2960101 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19