Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5019 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.9047. Min Act: -0.1700
Data Index: 7296831 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.8422. Min Act: -0.1700
Data Index: 2477073 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.7172. Min Act: -0.1700
Data Index: 3894684 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.6859. Min Act: -0.1700
Data Index: 2028474 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.6234. Min Act: -0.1700
Data Index: 1773779 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5922. Min Act: -0.1700
Data Index: 2668217 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5609. Min Act: -0.1700
Data Index: 4925519 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5297. Min Act: -0.1700
Data Index: 7381068 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5609. Min Act: -0.1700
Data Index: 5373578 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5297. Min Act: -0.1700
Data Index: 5481937 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5297. Min Act: -0.1700
Data Index: 6548902 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3003645 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4984. Min Act: -0.1700
Data Index: 7294670 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6855974 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 4475867 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4672. Min Act: -0.1700
Data Index: 320658 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4359. Min Act: -0.1700
Data Index: 6001757 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4359. Min Act: -0.1700
Data Index: 7224994 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4047. Min Act: -0.1700
Data Index: 1487897 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9047. Min Range: -5.9047
Max Act: 5.4047. Min Act: -0.1700
Data Index: 1862944 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19