Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 3072453 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 444724 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 886504 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 713281 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9324. Min Act: -0.1700
Data Index: 1830587 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9324. Min Act: -0.1700
Data Index: 3887964 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9011. Min Act: -0.1700
Data Index: 6979192 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.8386. Min Act: -0.1700
Data Index: 6338249 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.8074. Min Act: -0.1700
Data Index: 1297579 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.8074. Min Act: -0.1700
Data Index: 4351191 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.8074. Min Act: -0.1700
Data Index: 3563928 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.8074. Min Act: -0.1700
Data Index: 5097581 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7761. Min Act: -0.1700
Data Index: 192473 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 148567 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 6721550 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 3766774 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 8399757 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7136. Min Act: -0.1700
Data Index: 5314142 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 4865102 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 4018208 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19