Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2796. Min Range: -6.2796
Max Act: 6.2796. Min Act: -0.1700
Data Index: 5913050 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2796. Min Range: -6.2796
Max Act: 6.2483. Min Act: -0.1700
Data Index: 4510715 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2796. Min Range: -6.2796
Max Act: 6.1858. Min Act: -0.1700
Data Index: 1864984 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2796. Min Range: -6.2796
Max Act: 6.1858. Min Act: -0.1700
Data Index: 408387 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2796. Min Range: -6.2796
Max Act: 6.0608. Min Act: -0.1700
Data Index: 7023099 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.9983. Min Act: -0.1700
Data Index: 7627225 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.9983. Min Act: -0.1700
Data Index: 7639945 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.9046. Min Act: -0.1700
Data Index: 2388252 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.9358. Min Act: -0.1700
Data Index: 8128925 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.8733. Min Act: -0.1700
Data Index: 8128939 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.9046. Min Act: -0.1700
Data Index: 5013030 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.8421. Min Act: -0.1700
Data Index: 6790000 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.8421. Min Act: -0.1700
Data Index: 5798840 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.8421. Min Act: -0.1700
Data Index: 5798841 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.8108. Min Act: -0.1700
Data Index: 2826973 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.7796. Min Act: -0.1700
Data Index: 28114 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.7483. Min Act: -0.1700
Data Index: 612835 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.7483. Min Act: -0.1700
Data Index: 4410999 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.7483. Min Act: -0.1700
Data Index: 3519207 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2796. Min Range: -6.2796
Max Act: 5.7796. Min Act: -0.1700
Data Index: 3765757 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19