Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 811 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.5925. Min Act: -0.1700
Data Index: 1241761 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.4988. Min Act: -0.1700
Data Index: 8616201 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.5300. Min Act: -0.1700
Data Index: 1242192 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.4675. Min Act: -0.1700
Data Index: 2994703 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.4675. Min Act: -0.1700
Data Index: 3648867 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.4675. Min Act: -0.1700
Data Index: 8076222 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5056055 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3425. Min Act: -0.1700
Data Index: 5639168 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3425. Min Act: -0.1700
Data Index: 7811704 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3425. Min Act: -0.1700
Data Index: 7526991 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3113. Min Act: -0.1700
Data Index: 6370550 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3113. Min Act: -0.1700
Data Index: 3509722 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.3113. Min Act: -0.1700
Data Index: 2263273 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.2800. Min Act: -0.1700
Data Index: 5066915 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.2800. Min Act: -0.1700
Data Index: 4396040 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.2488. Min Act: -0.1700
Data Index: 4202410 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.2488. Min Act: -0.1700
Data Index: 2482260 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.2488. Min Act: -0.1700
Data Index: 7730938 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.1863. Min Act: -0.1700
Data Index: 5572477 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5925. Min Range: -6.5925
Max Act: 6.2488. Min Act: -0.1700
Data Index: 1441732 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19