Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.8801. Min Act: -0.1700
Data Index: 5443813 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.6301. Min Act: -0.1700
Data Index: 8483068 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.4113. Min Act: -0.1700
Data Index: 1144314 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.3801. Min Act: -0.1700
Data Index: 593363 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.3801. Min Act: -0.1700
Data Index: 740302 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.3488. Min Act: -0.1700
Data Index: 969581 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.3801. Min Act: -0.1700
Data Index: 4743646 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.3176. Min Act: -0.1700
Data Index: 6258975 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.3176. Min Act: -0.1700
Data Index: 1381957 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.2551. Min Act: -0.1700
Data Index: 5939920 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.2551. Min Act: -0.1700
Data Index: 1715050 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.2551. Min Act: -0.1700
Data Index: 490888 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.2238. Min Act: -0.1700
Data Index: 1013331 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.2238. Min Act: -0.1700
Data Index: 1890981 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.2238. Min Act: -0.1700
Data Index: 1088419 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.1926. Min Act: -0.1700
Data Index: 4648472 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.1926. Min Act: -0.1700
Data Index: 3331440 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.1926. Min Act: -0.1700
Data Index: 8071428 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.1926. Min Act: -0.1700
Data Index: 6291499 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8801. Min Range: -5.8801
Max Act: 5.1926. Min Act: -0.1700
Data Index: 6278056 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19