Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.9590. Min Act: -0.1700
Data Index: 2475968 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.9277. Min Act: -0.1700
Data Index: 4117144 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7715. Min Act: -0.1700
Data Index: 3526319 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7715. Min Act: -0.1700
Data Index: 7067045 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7402. Min Act: -0.1700
Data Index: 6797856 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7402. Min Act: -0.1700
Data Index: 3529031 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7402. Min Act: -0.1700
Data Index: 4426113 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7090. Min Act: -0.1700
Data Index: 623956 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7090. Min Act: -0.1700
Data Index: 6152465 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7090. Min Act: -0.1700
Data Index: 819132 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7090. Min Act: -0.1700
Data Index: 3641756 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6777. Min Act: -0.1700
Data Index: 8501729 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.7090. Min Act: -0.1700
Data Index: 1948639 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6465. Min Act: -0.1700
Data Index: 3433361 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6152. Min Act: -0.1700
Data Index: 5180450 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6465. Min Act: -0.1700
Data Index: 931546 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6152. Min Act: -0.1700
Data Index: 4170729 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6152. Min Act: -0.1700
Data Index: 6629718 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6152. Min Act: -0.1700
Data Index: 2242717 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9590. Min Range: -5.9590
Max Act: 5.6152. Min Act: -0.1700
Data Index: 325297 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19