Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.8682. Min Act: -0.1700
Data Index: 8207641 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.8057. Min Act: -0.1700
Data Index: 1697982 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.8057. Min Act: -0.1700
Data Index: 2383770 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.7744. Min Act: -0.1700
Data Index: 2100801 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.7432. Min Act: -0.1700
Data Index: 8599578 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.6807. Min Act: -0.1700
Data Index: 7265263 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.6494. Min Act: -0.1700
Data Index: 4029309 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.6182. Min Act: -0.1700
Data Index: 7118648 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.6494. Min Act: -0.1700
Data Index: 8582085 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.6182. Min Act: -0.1700
Data Index: 7299216 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.5869. Min Act: -0.1700
Data Index: 6635007 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.5557. Min Act: -0.1700
Data Index: 6056637 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.5869. Min Act: -0.1700
Data Index: 7363304 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.5244. Min Act: -0.1700
Data Index: 4218165 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.5244. Min Act: -0.1700
Data Index: 3099982 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.4932. Min Act: -0.1700
Data Index: 1308195 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.4619. Min Act: -0.1700
Data Index: 221809 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.4307. Min Act: -0.1700
Data Index: 3321308 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.4619. Min Act: -0.1700
Data Index: 6347425 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8682. Min Range: -4.8682
Max Act: 4.4619. Min Act: -0.1700
Data Index: 6397109 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19