Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1806 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.4619. Min Act: -0.1700
Data Index: 1960352 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.4307. Min Act: -0.1700
Data Index: 1432452 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.3682. Min Act: -0.1700
Data Index: 620168 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.3057. Min Act: -0.1700
Data Index: 6671835 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.2432. Min Act: -0.1700
Data Index: 1873328 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.2119. Min Act: -0.1700
Data Index: 5581376 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.2119. Min Act: -0.1700
Data Index: 6614864 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.2119. Min Act: -0.1700
Data Index: 6810425 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1807. Min Act: -0.1700
Data Index: 3016115 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1807. Min Act: -0.1700
Data Index: 8276552 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1807. Min Act: -0.1700
Data Index: 6815499 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1494. Min Act: -0.1700
Data Index: 8707099 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1494. Min Act: -0.1700
Data Index: 6562600 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1182. Min Act: -0.1700
Data Index: 3587749 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.1182. Min Act: -0.1700
Data Index: 1837024 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.0869. Min Act: -0.1700
Data Index: 7123922 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.0869. Min Act: -0.1700
Data Index: 7165186 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.0557. Min Act: -0.1700
Data Index: 4662168 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.0557. Min Act: -0.1700
Data Index: 246184 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4619. Min Range: -5.4619
Max Act: 5.0557. Min Act: -0.1700
Data Index: 3001586 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19