Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2274. Min Range: -9.2274
Max Act: 9.2274. Min Act: -0.1700
Data Index: 7207441 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.7899. Min Act: -0.1700
Data Index: 7384746 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.4149. Min Act: -0.1700
Data Index: 6321044 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 5720906 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 595424 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 1438390 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.2899. Min Act: -0.1700
Data Index: 7497127 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 102417 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 6670893 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 579276 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 1852321 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 4877287 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.2274. Min Act: -0.1700
Data Index: 484573 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.2274. Min Act: -0.1700
Data Index: 4483308 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.2274. Min Act: -0.1700
Data Index: 2396046 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.2274. Min Act: -0.1700
Data Index: 2011509 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.2274. Min Act: -0.1700
Data Index: 4323180 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.1649. Min Act: -0.1700
Data Index: 5404992 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.1649. Min Act: -0.1700
Data Index: 1685314 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2274. Min Range: -9.2274
Max Act: 8.1649. Min Act: -0.1700
Data Index: 2293478 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19