Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5934 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.4049. Min Act: -0.1700
Data Index: 2882083 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.3424. Min Act: -0.1700
Data Index: 4132523 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.3737. Min Act: -0.1700
Data Index: 5654677 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.2799. Min Act: -0.1700
Data Index: 1466178 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1862. Min Act: -0.1700
Data Index: 4495487 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.1549. Min Act: -0.1700
Data Index: 3766236 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0924. Min Act: -0.1700
Data Index: 6584784 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0612. Min Act: -0.1696
Data Index: 3795042 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0299. Min Act: -0.1700
Data Index: 7820098 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0299. Min Act: -0.1700
Data Index: 3743360 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0299. Min Act: -0.1700
Data Index: 3669121 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0299. Min Act: -0.1700
Data Index: 703888 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4049. Min Range: -5.4049
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4602519 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9987. Min Act: -0.1700
Data Index: 8333828 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9987. Min Act: -0.1700
Data Index: 6999103 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9987. Min Act: -0.1700
Data Index: 1853061 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9362. Min Act: -0.1700
Data Index: 5228793 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9674. Min Act: -0.1700
Data Index: 5148306 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9362. Min Act: -0.1700
Data Index: 7179142 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4049. Min Range: -5.4049
Max Act: 4.9362. Min Act: -0.1700
Data Index: 6247545 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19