Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5462 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.9759. Min Act: -0.1700
Data Index: 8792128 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.7884. Min Act: -0.1700
Data Index: 6513432 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.6321. Min Act: -0.1700
Data Index: 5400984 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.6009. Min Act: -0.1700
Data Index: 4727322 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5384. Min Act: -0.1700
Data Index: 1941268 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5071. Min Act: -0.1700
Data Index: 3474627 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.5071. Min Act: -0.1700
Data Index: 357490 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4134. Min Act: -0.1700
Data Index: 3093022 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.4134. Min Act: -0.1700
Data Index: 3139319 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3821. Min Act: -0.1700
Data Index: 5686493 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3821. Min Act: -0.1700
Data Index: 7672176 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3821. Min Act: -0.1700
Data Index: 4767184 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3821. Min Act: -0.1700
Data Index: 5148537 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3509. Min Act: -0.1700
Data Index: 1281549 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 4953487 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 4776215 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 1941266 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 2557918 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.3196. Min Act: -0.1700
Data Index: 3667805 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9759. Min Range: -5.9759
Max Act: 5.2884. Min Act: -0.1700
Data Index: 3486850 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19