Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.8781. Min Act: -0.1700
Data Index: 4835085 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.8156. Min Act: -0.1700
Data Index: 8665353 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.6592. Min Act: -0.1700
Data Index: 3265881 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.6592. Min Act: -0.1700
Data Index: 7720621 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.6279. Min Act: -0.1700
Data Index: 6571609 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.5966. Min Act: -0.1700
Data Index: 8665352 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.5183. Min Act: -0.1700
Data Index: 895681 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4870. Min Act: -0.1700
Data Index: 8650763 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4870. Min Act: -0.1700
Data Index: 4835086 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4713. Min Act: -0.1700
Data Index: 2250191 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4713. Min Act: -0.1700
Data Index: 7518272 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4556. Min Act: -0.1700
Data Index: 3308340 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4399. Min Act: -0.1700
Data Index: 5463903 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4086. Min Act: -0.1700
Data Index: 8102019 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.3929. Min Act: -0.1700
Data Index: 6136610 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.4086. Min Act: -0.1700
Data Index: 2794459 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.3929. Min Act: -0.1700
Data Index: 7883146 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.3772. Min Act: -0.1700
Data Index: 1249980 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.3772. Min Act: -0.1700
Data Index: 6662697 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8781. Min Range: -3.8781
Max Act: 3.3772. Min Act: -0.1700
Data Index: 7118557 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19