Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5207 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.4321. Min Act: -0.1700
Data Index: 2621607 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.4321. Min Act: -0.1700
Data Index: 8363270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3696. Min Act: -0.1700
Data Index: 1793156 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3696. Min Act: -0.1700
Data Index: 8460939 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 1542861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 2311751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 1094253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 4726749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 1983190 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 4290515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 1772152 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 4265787 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2758. Min Act: -0.1700
Data Index: 8760447 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.3071. Min Act: -0.1700
Data Index: 8498451 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2758. Min Act: -0.1700
Data Index: 3266771 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2758. Min Act: -0.1700
Data Index: 521918 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2758. Min Act: -0.1700
Data Index: 3719671 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2446. Min Act: -0.1700
Data Index: 4571178 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2446. Min Act: -0.1700
Data Index: 7656405 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2446. Min Act: -0.1700
Data Index: 7580289 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19