Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4265. Min Range: -7.4265
Max Act: 7.4265. Min Act: -0.1700
Data Index: 7038873 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4265. Min Range: -7.4265
Max Act: 7.1140. Min Act: -0.1700
Data Index: 1474586 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.8640. Min Act: -0.1700
Data Index: 1178661 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.8328. Min Act: -0.1700
Data Index: 1388214 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.8015. Min Act: -0.1700
Data Index: 1360311 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.6765. Min Act: -0.1700
Data Index: 3745755 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.6453. Min Act: -0.1700
Data Index: 1417254 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.5515. Min Act: -0.1700
Data Index: 3844793 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.4890. Min Act: -0.1700
Data Index: 2532916 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.4890. Min Act: -0.1700
Data Index: 6886500 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.4265. Min Act: -0.1700
Data Index: 4076906 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.4265. Min Act: -0.1700
Data Index: 1957407 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.4265. Min Act: -0.1700
Data Index: 5872803 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.3328. Min Act: -0.1700
Data Index: 5186874 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.3328. Min Act: -0.1700
Data Index: 5082505 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.3015. Min Act: -0.1700
Data Index: 1998600 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.2703. Min Act: -0.1700
Data Index: 491058 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7273668 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.1765. Min Act: -0.1700
Data Index: 5869320 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4265. Min Range: -7.4265
Max Act: 6.2078. Min Act: -0.1700
Data Index: 3562436 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19