Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.7594. Min Act: -0.1700
Data Index: 4567978 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.6032. Min Act: -0.1700
Data Index: 108056 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.5719. Min Act: -0.1700
Data Index: 5311283 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.5719. Min Act: -0.1700
Data Index: 5141171 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.4157. Min Act: -0.1700
Data Index: 7787728 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.3844. Min Act: -0.1700
Data Index: 6525869 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.3844. Min Act: -0.1700
Data Index: 3429729 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.3532. Min Act: -0.1700
Data Index: 8203904 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.3219. Min Act: -0.1700
Data Index: 5148916 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.3219. Min Act: -0.1700
Data Index: 7184255 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2907. Min Act: -0.1700
Data Index: 5857407 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2594. Min Act: -0.1700
Data Index: 1151308 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2907. Min Act: -0.1700
Data Index: 1179466 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2594. Min Act: -0.1700
Data Index: 1291061 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2282. Min Act: -0.1700
Data Index: 2109047 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2282. Min Act: -0.1700
Data Index: 4502733 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2594. Min Act: -0.1700
Data Index: 1766471 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2282. Min Act: -0.1700
Data Index: 5710017 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2282. Min Act: -0.1700
Data Index: 3758922 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7594. Min Range: -5.7594
Max Act: 5.2594. Min Act: -0.1700
Data Index: 622993 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19