Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5705. Min Act: -0.1700
Data Index: 906883 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5080. Min Act: -0.1700
Data Index: 4432265 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5392. Min Act: -0.1700
Data Index: 4037545 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5080. Min Act: -0.1700
Data Index: 4338355 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4767. Min Act: -0.1700
Data Index: 8613622 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.5080. Min Act: -0.1700
Data Index: 4124546 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4455. Min Act: -0.1700
Data Index: 1981030 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4455. Min Act: -0.1700
Data Index: 4813555 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3830. Min Act: -0.1700
Data Index: 7507984 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4142. Min Act: -0.1700
Data Index: 1490874 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4142. Min Act: -0.1700
Data Index: 5729023 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.4142. Min Act: -0.1700
Data Index: 7458697 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3830. Min Act: -0.1700
Data Index: 5776624 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3830. Min Act: -0.1700
Data Index: 5407573 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3517. Min Act: -0.1700
Data Index: 1576091 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3517. Min Act: -0.1700
Data Index: 313223 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3205. Min Act: -0.1700
Data Index: 6094029 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3205. Min Act: -0.1700
Data Index: 986863 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.2892. Min Act: -0.1700
Data Index: 1561005 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5705. Min Range: -6.5705
Max Act: 6.3205. Min Act: -0.1700
Data Index: 917519 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19