Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4304 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0452. Min Range: -9.0452
Max Act: 9.0452. Min Act: -0.1700
Data Index: 916942 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.9827. Min Act: -0.1700
Data Index: 950620 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.9202. Min Act: -0.1700
Data Index: 3502787 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.8577. Min Act: -0.1700
Data Index: 6783581 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.7952. Min Act: -0.1700
Data Index: 4587026 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.7952. Min Act: -0.1700
Data Index: 5227092 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.7952. Min Act: -0.1700
Data Index: 4230921 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.7952. Min Act: -0.1700
Data Index: 6872088 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.7327. Min Act: -0.1700
Data Index: 8308685 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.6702. Min Act: -0.1700
Data Index: 7221789 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.6702. Min Act: -0.1700
Data Index: 7879438 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.6702. Min Act: -0.1700
Data Index: 5026629 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.6702. Min Act: -0.1700
Data Index: 1393339 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.6077. Min Act: -0.1700
Data Index: 5220490 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.4827. Min Act: -0.1700
Data Index: 4773983 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.5452. Min Act: -0.1700
Data Index: 6114322 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.5452. Min Act: -0.1700
Data Index: 302509 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.5452. Min Act: -0.1700
Data Index: 1466559 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.5452. Min Act: -0.1700
Data Index: 7749113 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0452. Min Range: -9.0452
Max Act: 8.4827. Min Act: -0.1700
Data Index: 7707520 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19