Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.5198. Min Act: -0.1700
Data Index: 8688461 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.3011. Min Act: -0.1700
Data Index: 722817 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.2698. Min Act: -0.1700
Data Index: 3488537 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.2386. Min Act: -0.1700
Data Index: 8086421 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.2698. Min Act: -0.1700
Data Index: 6191003 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.2073. Min Act: -0.1700
Data Index: 1836354 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.2386. Min Act: -0.1700
Data Index: 7495601 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.2073. Min Act: -0.1700
Data Index: 3787897 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1761. Min Act: -0.1700
Data Index: 3921213 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1761. Min Act: -0.1700
Data Index: 904389 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1761. Min Act: -0.1700
Data Index: 3739407 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1761. Min Act: -0.1700
Data Index: 7144818 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1448. Min Act: -0.1700
Data Index: 1328265 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1136. Min Act: -0.1700
Data Index: 3019576 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1136. Min Act: -0.1700
Data Index: 722816 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1448. Min Act: -0.1700
Data Index: 7779709 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1448. Min Act: -0.1700
Data Index: 2198927 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1136. Min Act: -0.1700
Data Index: 3416464 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1136. Min Act: -0.1700
Data Index: 4821445 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5198. Min Range: -5.5198
Max Act: 5.1136. Min Act: -0.1700
Data Index: 5724308 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19