Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.4862. Min Act: -0.1700
Data Index: 3512648 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.3924. Min Act: -0.1700
Data Index: 5175414 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.3299. Min Act: -0.1700
Data Index: 7520460 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.2674. Min Act: -0.1700
Data Index: 463970 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.2049. Min Act: -0.1700
Data Index: 2772014 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.1112. Min Act: -0.1700
Data Index: 8078534 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.0799. Min Act: -0.1700
Data Index: 7458997 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.0799. Min Act: -0.1700
Data Index: 1804330 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.0487. Min Act: -0.1700
Data Index: 6258347 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.0487. Min Act: -0.1700
Data Index: 1563847 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.9862. Min Act: -0.1700
Data Index: 1142568 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.0174. Min Act: -0.1700
Data Index: 6076927 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4862. Min Range: -7.4862
Max Act: 7.0174. Min Act: -0.1700
Data Index: 8829778 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.9237. Min Act: -0.1700
Data Index: 7458987 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.9237. Min Act: -0.1700
Data Index: 847170 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.9237. Min Act: -0.1700
Data Index: 7198896 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.8924. Min Act: -0.1700
Data Index: 5639432 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.8924. Min Act: -0.1700
Data Index: 6892110 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.8612. Min Act: -0.1700
Data Index: 1558940 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4862. Min Range: -7.4862
Max Act: 6.8612. Min Act: -0.1700
Data Index: 4282290 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19