Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.7376. Min Act: -0.1700
Data Index: 2719655 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.3313. Min Act: -0.1700
Data Index: 3303786 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.1751. Min Act: -0.1700
Data Index: 4338711 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.1438. Min Act: -0.1700
Data Index: 8816467 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.1438. Min Act: -0.1700
Data Index: 260279 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.1126. Min Act: -0.1700
Data Index: 4492523 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.0501. Min Act: -0.1700
Data Index: 6619660 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.0501. Min Act: -0.1700
Data Index: 189708 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.0188. Min Act: -0.1700
Data Index: 2822966 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.0188. Min Act: -0.1700
Data Index: 5729865 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.0188. Min Act: -0.1700
Data Index: 7942821 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7376. Min Range: -5.7376
Max Act: 5.0188. Min Act: -0.1700
Data Index: 330498 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9876. Min Act: -0.1700
Data Index: 8643114 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9876. Min Act: -0.1700
Data Index: 2320562 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9876. Min Act: -0.1700
Data Index: 6054494 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9251. Min Act: -0.1700
Data Index: 3291453 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9563. Min Act: -0.1700
Data Index: 310089 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9563. Min Act: -0.1700
Data Index: 5235376 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9563. Min Act: -0.1700
Data Index: 451763 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7376. Min Range: -5.7376
Max Act: 4.9563. Min Act: -0.1700
Data Index: 4038175 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19