Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5282 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2157. Min Range: -8.2157
Max Act: 8.2157. Min Act: -0.1700
Data Index: 559171 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2157. Min Range: -8.2157
Max Act: 8.1532. Min Act: -0.1700
Data Index: 7338628 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2157. Min Range: -8.2157
Max Act: 8.0282. Min Act: -0.1700
Data Index: 53593 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.9657. Min Act: -0.1700
Data Index: 4118827 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.7782. Min Act: -0.1700
Data Index: 3270615 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.7470. Min Act: -0.1700
Data Index: 4291443 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.7157. Min Act: -0.1700
Data Index: 2551539 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.6845. Min Act: -0.1700
Data Index: 931852 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.6220. Min Act: -0.1700
Data Index: 1260114 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5907. Min Act: -0.1700
Data Index: 728370 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5907. Min Act: -0.1700
Data Index: 2097732 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5907. Min Act: -0.1700
Data Index: 2735872 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5907. Min Act: -0.1700
Data Index: 5023566 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5595. Min Act: -0.1700
Data Index: 4060784 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5595. Min Act: -0.1700
Data Index: 3301281 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5595. Min Act: -0.1700
Data Index: 1657801 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.5282. Min Act: -0.1700
Data Index: 7880813 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.4970. Min Act: -0.1700
Data Index: 17950 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.4657. Min Act: -0.1700
Data Index: 5417642 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2157. Min Range: -8.2157
Max Act: 7.4970. Min Act: -0.1700
Data Index: 4123301 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19