Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2133. Min Range: -7.2133
Max Act: 7.2133. Min Act: -0.1700
Data Index: 1472354 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2133. Min Range: -7.2133
Max Act: 7.1508. Min Act: -0.1700
Data Index: 4650053 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2133. Min Range: -7.2133
Max Act: 7.0883. Min Act: -0.1700
Data Index: 1384537 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2133. Min Range: -7.2133
Max Act: 7.0570. Min Act: -0.1700
Data Index: 6211770 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.9633. Min Act: -0.1700
Data Index: 6294593 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.9320. Min Act: -0.1700
Data Index: 7076133 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.9008. Min Act: -0.1700
Data Index: 1472350 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.9008. Min Act: -0.1700
Data Index: 7559648 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.8695. Min Act: -0.1700
Data Index: 2489635 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.8383. Min Act: -0.1700
Data Index: 6065279 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.8383. Min Act: -0.1700
Data Index: 3275011 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.8383. Min Act: -0.1700
Data Index: 8128579 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7758. Min Act: -0.1700
Data Index: 5912105 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7758. Min Act: -0.1700
Data Index: 6602304 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7758. Min Act: -0.1700
Data Index: 5625579 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7758. Min Act: -0.1700
Data Index: 4567857 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7445. Min Act: -0.1700
Data Index: 4267175 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 3317667 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 7835506 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2133. Min Range: -7.2133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 1582780 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19