Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1584 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2380. Min Range: -4.2380
Max Act: 4.2380. Min Act: -0.1700
Data Index: 7257459 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2380. Min Range: -4.2380
Max Act: 4.0818. Min Act: -0.1700
Data Index: 7842917 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2380. Min Range: -4.2380
Max Act: 4.0192. Min Act: -0.1700
Data Index: 472380 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9880. Min Act: -0.1700
Data Index: 6978285 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9567. Min Act: -0.1700
Data Index: 3284460 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9880. Min Act: -0.1700
Data Index: 3377162 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9567. Min Act: -0.1700
Data Index: 4222935 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 235147 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 1416748 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9411. Min Act: -0.1700
Data Index: 4711377 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 7099285 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 2485975 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 2788509 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9411. Min Act: -0.1700
Data Index: 3377161 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9098. Min Act: -0.1700
Data Index: 2010644 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 881810 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9098. Min Act: -0.1700
Data Index: 1431454 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9098. Min Act: -0.1700
Data Index: 7089794 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9098. Min Act: -0.1700
Data Index: 5890080 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2380. Min Range: -4.2380
Max Act: 3.9255. Min Act: -0.1700
Data Index: 6243901 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19