Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.9399. Min Act: -0.1700
Data Index: 6222459 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.7524. Min Act: -0.1700
Data Index: 1570702 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.6899. Min Act: -0.1700
Data Index: 3271143 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.6274. Min Act: -0.1700
Data Index: 4938245 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.5649. Min Act: -0.1700
Data Index: 1880810 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.4399. Min Act: -0.1700
Data Index: 2078854 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.3774. Min Act: -0.1699
Data Index: 6149820 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.3774. Min Act: -0.1700
Data Index: 3830801 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.3149. Min Act: -0.1700
Data Index: 4038544 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.3149. Min Act: -0.1700
Data Index: 3342593 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.2524. Min Act: -0.1700
Data Index: 6982219 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1274. Min Act: -0.1700
Data Index: 5711497 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1899. Min Act: -0.1700
Data Index: 4897523 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1899. Min Act: -0.1700
Data Index: 8179104 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1274. Min Act: -0.1700
Data Index: 6673514 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1274. Min Act: -0.1700
Data Index: 2404535 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1274. Min Act: -0.1700
Data Index: 200025 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1274. Min Act: -0.1700
Data Index: 1460938 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.0649. Min Act: -0.1700
Data Index: 1210482 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9399. Min Range: -10.9399
Max Act: 10.1274. Min Act: -0.1700
Data Index: 7499794 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19