Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3342 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.5980. Min Act: -0.1700
Data Index: 7960548 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.4105. Min Act: -0.1700
Data Index: 6494273 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.3167. Min Act: -0.1700
Data Index: 655978 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2855. Min Act: -0.1700
Data Index: 605769 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2542. Min Act: -0.1700
Data Index: 437653 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2542. Min Act: -0.1700
Data Index: 103760 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2855. Min Act: -0.1700
Data Index: 990355 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2230. Min Act: -0.1700
Data Index: 3772657 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2230. Min Act: -0.1700
Data Index: 7481465 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.2230. Min Act: -0.1700
Data Index: 4488522 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1917. Min Act: -0.1700
Data Index: 7757440 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1917. Min Act: -0.1700
Data Index: 687271 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1917. Min Act: -0.1700
Data Index: 886220 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1917. Min Act: -0.1700
Data Index: 4690605 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1292. Min Act: -0.1700
Data Index: 2241992 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1605. Min Act: -0.1700
Data Index: 8108843 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1605. Min Act: -0.1700
Data Index: 7039561 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1605. Min Act: -0.1700
Data Index: 4706243 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1605. Min Act: -0.1700
Data Index: 7488795 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5980. Min Range: -4.5980
Max Act: 4.1292. Min Act: -0.1700
Data Index: 4132799 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19