Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1737 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.4084. Min Act: -0.1700
Data Index: 8667477 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.4084. Min Act: -0.1700
Data Index: 8421143 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.3459. Min Act: -0.1700
Data Index: 250362 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.3146. Min Act: -0.1700
Data Index: 2341763 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2834. Min Act: -0.1700
Data Index: 2599354 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2834. Min Act: -0.1700
Data Index: 4560273 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2521. Min Act: -0.1700
Data Index: 5774288 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2521. Min Act: -0.1700
Data Index: 1691117 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2521. Min Act: -0.1700
Data Index: 7074623 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 2868876 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1896. Min Act: -0.1700
Data Index: 4229517 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1896. Min Act: -0.1700
Data Index: 6550341 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1896. Min Act: -0.1700
Data Index: 5015557 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1584. Min Act: -0.1700
Data Index: 6063343 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1584. Min Act: -0.1700
Data Index: 6956037 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1271. Min Act: -0.1700
Data Index: 6888116 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.0959. Min Act: -0.1700
Data Index: 6348518 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1271. Min Act: -0.1700
Data Index: 5349424 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.0959. Min Act: -0.1700
Data Index: 5486180 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1271. Min Act: -0.1700
Data Index: 3699438 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19