Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.9513. Min Act: -0.1700
Data Index: 5511039 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.5763. Min Act: -0.1700
Data Index: 233281 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.5138. Min Act: -0.1700
Data Index: 1840920 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.4201. Min Act: -0.1700
Data Index: 1435700 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.3576. Min Act: -0.1700
Data Index: 633731 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.1388. Min Act: -0.1700
Data Index: 5004827 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.1388. Min Act: -0.1700
Data Index: 565091 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.1388. Min Act: -0.1700
Data Index: 2614601 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9513. Min Range: -7.9513
Max Act: 7.0138. Min Act: -0.1700
Data Index: 7831393 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.9826. Min Act: -0.1700
Data Index: 4848920 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.9513. Min Act: -0.1700
Data Index: 4162193 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.9201. Min Act: -0.1700
Data Index: 5648360 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.9201. Min Act: -0.1700
Data Index: 1763880 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.9201. Min Act: -0.1700
Data Index: 1058746 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.8576. Min Act: -0.1700
Data Index: 6970787 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.8263. Min Act: -0.1700
Data Index: 570675 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.8263. Min Act: -0.1700
Data Index: 884849 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.8263. Min Act: -0.1700
Data Index: 1668707 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.7951. Min Act: -0.1700
Data Index: 993521 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9513. Min Range: -7.9513
Max Act: 6.7638. Min Act: -0.1700
Data Index: 4083983 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19