Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2804. Min Act: -0.1700
Data Index: 6203902 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.3275. Min Act: -0.1700
Data Index: 7937922 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2961. Min Act: -0.1700
Data Index: 84117 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2490. Min Act: -0.1700
Data Index: 3595794 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2961. Min Act: -0.1700
Data Index: 3754408 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2647. Min Act: -0.1700
Data Index: 5604198 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2647. Min Act: -0.1700
Data Index: 6491278 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2647. Min Act: -0.1700
Data Index: 248724 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2175. Min Act: -0.1700
Data Index: 5501785 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2332. Min Act: -0.1700
Data Index: 815449 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2018. Min Act: -0.1700
Data Index: 3052949 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2332. Min Act: -0.1700
Data Index: 5212707 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2018. Min Act: -0.1700
Data Index: 5085823 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2018. Min Act: -0.1700
Data Index: 1231465 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2175. Min Act: -0.1700
Data Index: 4175579 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2175. Min Act: -0.1700
Data Index: 2567812 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2175. Min Act: -0.1700
Data Index: 6866097 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.1861. Min Act: -0.1700
Data Index: 4216005 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.2175. Min Act: -0.1700
Data Index: 2857655 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.1861. Min Act: -0.1700
Data Index: 6128064 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19