Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.4582. Min Act: -0.1700
Data Index: 2333628 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.4425. Min Act: -0.1700
Data Index: 2995614 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3484. Min Act: -0.1700
Data Index: 2735772 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3641. Min Act: -0.1700
Data Index: 2995616 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3327. Min Act: -0.1700
Data Index: 7207064 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3327. Min Act: -0.1700
Data Index: 8060020 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3171. Min Act: -0.1700
Data Index: 3441817 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2857. Min Act: -0.1700
Data Index: 7327218 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2857. Min Act: -0.1700
Data Index: 1634229 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2857. Min Act: -0.1700
Data Index: 7841668 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2857. Min Act: -0.1700
Data Index: 5005989 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3014. Min Act: -0.1700
Data Index: 3666178 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.3014. Min Act: -0.1700
Data Index: 6644628 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2857. Min Act: -0.1700
Data Index: 1332255 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2857. Min Act: -0.1700
Data Index: 4783797 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2700. Min Act: -0.1700
Data Index: 1937539 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2700. Min Act: -0.1700
Data Index: 7310969 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2542. Min Act: -0.1700
Data Index: 6704397 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2700. Min Act: -0.1700
Data Index: 6765176 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4582. Min Range: -3.4582
Max Act: 3.2542. Min Act: -0.1700
Data Index: 2521365 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19