Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8467. Min Act: -0.1700
Data Index: 3930190 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8780. Min Act: -0.1700
Data Index: 8653549 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8467. Min Act: -0.1700
Data Index: 5799879 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8467. Min Act: -0.1700
Data Index: 8462175 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8155. Min Act: -0.1700
Data Index: 5077040 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8155. Min Act: -0.1700
Data Index: 2317277 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.8155. Min Act: -0.1700
Data Index: 4817378 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.7842. Min Act: -0.1700
Data Index: 1950456 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.7530. Min Act: -0.1700
Data Index: 809540 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.7217. Min Act: -0.1700
Data Index: 7039799 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.7217. Min Act: -0.1700
Data Index: 872922 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.6592. Min Act: -0.1700
Data Index: 2993362 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.6280. Min Act: -0.1700
Data Index: 809539 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.6592. Min Act: -0.1700
Data Index: 2087594 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.6280. Min Act: -0.1700
Data Index: 3016855 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.6280. Min Act: -0.1700
Data Index: 1825064 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.6280. Min Act: -0.1700
Data Index: 935513 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.5967. Min Act: -0.1700
Data Index: 4759174 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.5967. Min Act: -0.1700
Data Index: 397096 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8780. Min Range: -5.8780
Max Act: 5.5655. Min Act: -0.1700
Data Index: 2048765 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19