Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4918 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0945. Min Range: -1.0945
Max Act: 1.0945. Min Act: -0.1700
Data Index: 1520075 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0945. Min Range: -1.0945
Max Act: 1.0508. Min Act: -0.1700
Data Index: 6849749 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9726. Min Act: -0.1695
Data Index: 3322460 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9553. Min Act: -0.1700
Data Index: 8791354 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9467. Min Act: -0.1699
Data Index: 1499276 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9553. Min Act: -0.1683
Data Index: 6424228 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9553. Min Act: -0.1677
Data Index: 2152309 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9381. Min Act: -0.1660
Data Index: 8478507 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9295. Min Act: -0.1698
Data Index: 6849750 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9295. Min Act: -0.1700
Data Index: 5454646 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9381. Min Act: -0.1700
Data Index: 2948293 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9295. Min Act: -0.1698
Data Index: 5350613 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9209. Min Act: -0.1700
Data Index: 8288890 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9038. Min Act: -0.1700
Data Index: 5569919 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9123. Min Act: -0.1700
Data Index: 2569792 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9123. Min Act: -0.1700
Data Index: 6236899 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9123. Min Act: -0.1699
Data Index: 888174 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9123. Min Act: -0.1700
Data Index: 3839040 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9038. Min Act: -0.1700
Data Index: 6214602 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0945. Min Range: -1.0945
Max Act: 0.9123. Min Act: -0.1697
Data Index: 4114006 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19