Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1998 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 4742891 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.9318. Min Act: -0.1700
Data Index: 6398087 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 2953041 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2269449 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2107807 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.7443. Min Act: -0.1700
Data Index: 7445590 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.7443. Min Act: -0.1700
Data Index: 7563377 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3700730 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.7443. Min Act: -0.1700
Data Index: 4880985 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.7131. Min Act: -0.1699
Data Index: 2887841 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6818. Min Act: -0.1700
Data Index: 319158 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 8320576 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 3700729 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6506. Min Act: -0.1700
Data Index: 6787259 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 3093342 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 5572785 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 3700731 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 164588 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 8059312 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9631. Min Range: -5.9631
Max Act: 5.6193. Min Act: -0.1700
Data Index: 4559497 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19