Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.4522. Min Act: -0.1700
Data Index: 2453130 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.3585. Min Act: -0.1700
Data Index: 6677178 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.2335. Min Act: -0.1700
Data Index: 4335869 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.2022. Min Act: -0.1700
Data Index: 4804709 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.1710. Min Act: -0.1700
Data Index: 7377785 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.1397. Min Act: -0.1700
Data Index: 2953899 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.1085. Min Act: -0.1700
Data Index: 850421 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0772. Min Act: -0.1700
Data Index: 4684306 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0460. Min Act: -0.1700
Data Index: 3508708 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0460. Min Act: -0.1700
Data Index: 4635263 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0460. Min Act: -0.1700
Data Index: 589135 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9835. Min Act: -0.1700
Data Index: 7525169 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9835. Min Act: -0.1700
Data Index: 389433 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1446955 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1173980 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9835. Min Act: -0.1700
Data Index: 472271 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0147. Min Act: -0.1700
Data Index: 7304880 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9835. Min Act: -0.1700
Data Index: 397422 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9522. Min Act: -0.1700
Data Index: 6377769 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9522. Min Act: -0.1700
Data Index: 160200 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19