Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3961 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.7282. Min Act: -0.1699
Data Index: 2398665 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8603054 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.4782. Min Act: -0.1700
Data Index: 2597819 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.5095. Min Act: -0.1700
Data Index: 3891985 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.5095. Min Act: -0.1700
Data Index: 7885303 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.4782. Min Act: -0.1700
Data Index: 2781034 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.4470. Min Act: -0.1700
Data Index: 7813140 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.4782. Min Act: -0.1700
Data Index: 5182929 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.4157. Min Act: -0.1700
Data Index: 4868727 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3845. Min Act: -0.1700
Data Index: 5054913 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.4157. Min Act: -0.1700
Data Index: 3091871 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3845. Min Act: -0.1699
Data Index: 7710799 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 3776261 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 1301431 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 8145163 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 8117944 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 1836636 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 2871502 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3532. Min Act: -0.1700
Data Index: 7788022 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7282. Min Range: -5.7282
Max Act: 5.3220. Min Act: -0.1700
Data Index: 1165544 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19