Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.3033. Min Act: -0.1700
Data Index: 922713 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.1783. Min Act: -0.1700
Data Index: 426101 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.1783. Min Act: -0.1700
Data Index: 8764302 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.1470. Min Act: -0.1700
Data Index: 2800310 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.1158. Min Act: -0.1700
Data Index: 4487539 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.0845. Min Act: -0.1700
Data Index: 2681143 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.0845. Min Act: -0.1700
Data Index: 5891878 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.0533. Min Act: -0.1700
Data Index: 1886528 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.0533. Min Act: -0.1700
Data Index: 3939843 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3033. Min Range: -4.3033
Max Act: 4.0220. Min Act: -0.1700
Data Index: 5069187 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9907. Min Act: -0.1700
Data Index: 1886491 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9907. Min Act: -0.1700
Data Index: 820513 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9907. Min Act: -0.1700
Data Index: 1578618 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9595. Min Act: -0.1700
Data Index: 1807766 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9595. Min Act: -0.1700
Data Index: 7526079 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9595. Min Act: -0.1700
Data Index: 784672 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9595. Min Act: -0.1700
Data Index: 7772252 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9595. Min Act: -0.1700
Data Index: 3182727 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9282. Min Act: -0.1700
Data Index: 7251987 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3033. Min Range: -4.3033
Max Act: 3.9282. Min Act: -0.1700
Data Index: 3654754 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19