Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.6741. Min Act: -0.1700
Data Index: 3215485 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.3929. Min Act: -0.1700
Data Index: 188379 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.2054. Min Act: -0.1700
Data Index: 1933115 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.1429. Min Act: -0.1700
Data Index: 7092660 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2442378 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0491. Min Act: -0.1700
Data Index: 5870184 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0491. Min Act: -0.1700
Data Index: 8517655 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0179. Min Act: -0.1700
Data Index: 3158393 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0491. Min Act: -0.1700
Data Index: 8544581 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0179. Min Act: -0.1700
Data Index: 3697883 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0179. Min Act: -0.1700
Data Index: 3835813 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0179. Min Act: -0.1700
Data Index: 4856949 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6741. Min Range: -6.6741
Max Act: 6.0179. Min Act: -0.1700
Data Index: 7815194 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.9866. Min Act: -0.1700
Data Index: 631113 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.9866. Min Act: -0.1700
Data Index: 1331150 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.9866. Min Act: -0.1700
Data Index: 2497318 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.9554. Min Act: -0.1700
Data Index: 2402105 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.9554. Min Act: -0.1700
Data Index: 8254634 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.9241. Min Act: -0.1700
Data Index: 4876674 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6741. Min Range: -6.6741
Max Act: 5.8929. Min Act: -0.1700
Data Index: 1666693 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19