Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.8590. Min Act: -0.1700
Data Index: 4411383 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.8278. Min Act: -0.1700
Data Index: 703144 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.7653. Min Act: -0.1700
Data Index: 4012752 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.7340. Min Act: -0.1700
Data Index: 1713120 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.7340. Min Act: -0.1700
Data Index: 8180156 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.7028. Min Act: -0.1700
Data Index: 2231723 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.6715. Min Act: -0.1700
Data Index: 8017295 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.6403. Min Act: -0.1700
Data Index: 1656411 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.6715. Min Act: -0.1700
Data Index: 7492361 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.6090. Min Act: -0.1700
Data Index: 1564148 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5778. Min Act: -0.1700
Data Index: 3370483 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5778. Min Act: -0.1700
Data Index: 4862487 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5465. Min Act: -0.1700
Data Index: 3807302 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5465. Min Act: -0.1700
Data Index: 306744 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5465. Min Act: -0.1700
Data Index: 1679107 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5153. Min Act: -0.1700
Data Index: 6211484 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5465. Min Act: -0.1700
Data Index: 6443455 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.5465. Min Act: -0.1700
Data Index: 2868687 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.4840. Min Act: -0.1700
Data Index: 7687322 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8590. Min Range: -6.8590
Max Act: 6.4528. Min Act: -0.1700
Data Index: 1095309 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19