Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4454 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.3133. Min Act: -0.1700
Data Index: 5955249 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.3133. Min Act: -0.1700
Data Index: 8771667 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.2508. Min Act: -0.1700
Data Index: 8100962 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.1258. Min Act: -0.1700
Data Index: 1399839 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.0946. Min Act: -0.1700
Data Index: 6871652 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.0633. Min Act: -0.1700
Data Index: 706199 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.0633. Min Act: -0.1700
Data Index: 6170805 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.0321. Min Act: -0.1700
Data Index: 8373438 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.0321. Min Act: -0.1700
Data Index: 1168488 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3133. Min Range: -6.3133
Max Act: 6.0008. Min Act: -0.1700
Data Index: 3847250 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9696. Min Act: -0.1700
Data Index: 3575025 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9696. Min Act: -0.1700
Data Index: 2368754 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9696. Min Act: -0.1700
Data Index: 8023799 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9696. Min Act: -0.1700
Data Index: 249880 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9696. Min Act: -0.1700
Data Index: 3341624 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9383. Min Act: -0.1700
Data Index: 2874744 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9383. Min Act: -0.1700
Data Index: 7130845 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9383. Min Act: -0.1700
Data Index: 7691259 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9383. Min Act: -0.1700
Data Index: 4067814 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3133. Min Range: -6.3133
Max Act: 5.9383. Min Act: -0.1700
Data Index: 3474020 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19