Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4600. Min Range: -6.4600
Max Act: 6.4600. Min Act: -0.1700
Data Index: 3373742 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4600. Min Range: -6.4600
Max Act: 6.0850. Min Act: -0.1700
Data Index: 303214 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.9600. Min Act: -0.1700
Data Index: 6472056 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.9600. Min Act: -0.1700
Data Index: 754666 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.9287. Min Act: -0.1700
Data Index: 5098397 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.8662. Min Act: -0.1700
Data Index: 3045829 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.8662. Min Act: -0.1700
Data Index: 6937384 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.8975. Min Act: -0.1700
Data Index: 7765132 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.8662. Min Act: -0.1700
Data Index: 724918 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.7725. Min Act: -0.1700
Data Index: 7535348 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.7725. Min Act: -0.1700
Data Index: 6419940 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.7412. Min Act: -0.1700
Data Index: 8521434 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.7412. Min Act: -0.1700
Data Index: 8322187 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.7412. Min Act: -0.1700
Data Index: 6503923 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.7100. Min Act: -0.1700
Data Index: 548935 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.6475. Min Act: -0.1700
Data Index: 8192952 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.6787. Min Act: -0.1700
Data Index: 4135020 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.6475. Min Act: -0.1700
Data Index: 6511652 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.6162. Min Act: -0.1700
Data Index: 3823946 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4600. Min Range: -6.4600
Max Act: 5.6162. Min Act: -0.1700
Data Index: 7312830 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19