Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.6527. Min Act: -0.1700
Data Index: 8146173 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.6215. Min Act: -0.1700
Data Index: 1614544 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.5902. Min Act: -0.1700
Data Index: 637990 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.5902. Min Act: -0.1700
Data Index: 3553269 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.5590. Min Act: -0.1700
Data Index: 4522471 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.5277. Min Act: -0.1700
Data Index: 321416 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4965. Min Act: -0.1700
Data Index: 4427535 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4965. Min Act: -0.1700
Data Index: 5664425 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4965. Min Act: -0.1700
Data Index: 4067680 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4652. Min Act: -0.1700
Data Index: 4991892 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4965. Min Act: -0.1700
Data Index: 3119390 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4652. Min Act: -0.1700
Data Index: 1380598 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4340. Min Act: -0.1700
Data Index: 2205318 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4652. Min Act: -0.1700
Data Index: 3845349 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4027. Min Act: -0.1700
Data Index: 6377995 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4027. Min Act: -0.1700
Data Index: 5118700 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.3714. Min Act: -0.1700
Data Index: 4142116 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4027. Min Act: -0.1700
Data Index: 3148143 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4027. Min Act: -0.1700
Data Index: 525501 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6527. Min Range: -4.6527
Max Act: 4.4027. Min Act: -0.1700
Data Index: 3845348 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19