Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4157 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0513. Min Range: -8.0513
Max Act: 8.0513. Min Act: -0.1700
Data Index: 1812607 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.8638. Min Act: -0.1700
Data Index: 3220761 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.9263. Min Act: -0.1700
Data Index: 3235066 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.8013. Min Act: -0.1700
Data Index: 4175826 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.7388. Min Act: -0.1700
Data Index: 907359 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.7388. Min Act: -0.1700
Data Index: 5014506 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6763. Min Act: -0.1700
Data Index: 5086436 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6138. Min Act: -0.1700
Data Index: 3086398 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6138. Min Act: -0.1700
Data Index: 5026164 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6138. Min Act: -0.1700
Data Index: 434668 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6138. Min Act: -0.1700
Data Index: 2891625 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6763. Min Act: -0.1700
Data Index: 2591472 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6138. Min Act: -0.1700
Data Index: 4993156 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.6138. Min Act: -0.1700
Data Index: 8810276 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.5513. Min Act: -0.1700
Data Index: 3192264 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.5513. Min Act: -0.1700
Data Index: 1616134 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.5513. Min Act: -0.1700
Data Index: 6170980 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.5200. Min Act: -0.1700
Data Index: 875081 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.5200. Min Act: -0.1700
Data Index: 3554397 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0513. Min Range: -8.0513
Max Act: 7.4888. Min Act: -0.1700
Data Index: 3707930 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19