Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3961 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.9195. Min Act: -0.1700
Data Index: 8734095 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3055159 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.4820. Min Act: -0.1700
Data Index: 5123298 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.4820. Min Act: -0.1700
Data Index: 4737529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.5133. Min Act: -0.1700
Data Index: 6911270 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.4820. Min Act: -0.1700
Data Index: 3533106 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.5133. Min Act: -0.1700
Data Index: 1413922 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.4508. Min Act: -0.1700
Data Index: 6735396 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.4508. Min Act: -0.1700
Data Index: 2472723 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3883. Min Act: -0.1700
Data Index: 2546309 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3570. Min Act: -0.1700
Data Index: 2349672 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3570. Min Act: -0.1700
Data Index: 6956624 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3570. Min Act: -0.1700
Data Index: 4270720 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3570. Min Act: -0.1700
Data Index: 7806525 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3258. Min Act: -0.1700
Data Index: 3068060 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3258. Min Act: -0.1700
Data Index: 1917532 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3258. Min Act: -0.1700
Data Index: 1328182 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3258. Min Act: -0.1700
Data Index: 7006 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3258. Min Act: -0.1700
Data Index: 4023054 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9195. Min Range: -5.9195
Max Act: 5.3258. Min Act: -0.1700
Data Index: 3342402 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19