Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.5430. Min Act: -0.1700
Data Index: 4784106 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.5430. Min Act: -0.1700
Data Index: 2748818 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.5118. Min Act: -0.1700
Data Index: 5780215 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.3868. Min Act: -0.1700
Data Index: 8315755 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.3555. Min Act: -0.1700
Data Index: 3451661 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.3243. Min Act: -0.1700
Data Index: 3877178 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.2930. Min Act: -0.1700
Data Index: 713945 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.3243. Min Act: -0.1700
Data Index: 1370244 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.2618. Min Act: -0.1700
Data Index: 3575254 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.2618. Min Act: -0.1700
Data Index: 26217 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.2618. Min Act: -0.1700
Data Index: 940409 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.2618. Min Act: -0.1700
Data Index: 3526804 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.2305. Min Act: -0.1700
Data Index: 3619957 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.1680. Min Act: -0.1700
Data Index: 6853756 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.1680. Min Act: -0.1700
Data Index: 3111260 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.1368. Min Act: -0.1700
Data Index: 3824585 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.1368. Min Act: -0.1700
Data Index: 2726572 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.1368. Min Act: -0.1700
Data Index: 4387942 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.0743. Min Act: -0.1700
Data Index: 1263365 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5430. Min Range: -5.5430
Max Act: 5.1055. Min Act: -0.1700
Data Index: 5815825 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19