Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.4074. Min Act: -0.1700
Data Index: 411055 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.3761. Min Act: -0.1700
Data Index: 4787580 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.2511. Min Act: -0.1700
Data Index: 498920 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1105182 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.1886. Min Act: -0.1700
Data Index: 1384177 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.1886. Min Act: -0.1700
Data Index: 256943 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.1886. Min Act: -0.1700
Data Index: 3446588 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.1886. Min Act: -0.1700
Data Index: 4129006 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0636. Min Act: -0.1700
Data Index: 653891 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.1574. Min Act: -0.1700
Data Index: 1571599 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0949. Min Act: -0.1700
Data Index: 6651614 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0949. Min Act: -0.1700
Data Index: 5334599 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0636. Min Act: -0.1700
Data Index: 2059232 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0011. Min Act: -0.1700
Data Index: 1385228 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0011. Min Act: -0.1700
Data Index: 8505113 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0011. Min Act: -0.1700
Data Index: 5867516 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4074. Min Range: -6.4074
Max Act: 6.0011. Min Act: -0.1700
Data Index: 7126959 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4074. Min Range: -6.4074
Max Act: 5.9699. Min Act: -0.1700
Data Index: 765624 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4074. Min Range: -6.4074
Max Act: 5.9386. Min Act: -0.1700
Data Index: 1440473 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4074. Min Range: -6.4074
Max Act: 5.9386. Min Act: -0.1700
Data Index: 5022951 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19