Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5012 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.6745. Min Act: -0.1700
Data Index: 3424100 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.6120. Min Act: -0.1700
Data Index: 7528404 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.5807. Min Act: -0.1700
Data Index: 5128984 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.4245. Min Act: -0.1700
Data Index: 3605662 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.3932. Min Act: -0.1700
Data Index: 8744720 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.3620. Min Act: -0.1700
Data Index: 3057464 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.3307. Min Act: -0.1700
Data Index: 2010493 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.3307. Min Act: -0.1700
Data Index: 877230 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.3307. Min Act: -0.1700
Data Index: 2858269 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2370. Min Act: -0.1700
Data Index: 822973 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2370. Min Act: -0.1700
Data Index: 4894941 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2682. Min Act: -0.1700
Data Index: 1699124 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2682. Min Act: -0.1700
Data Index: 5065650 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2370. Min Act: -0.1700
Data Index: 5153845 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6177116 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2370. Min Act: -0.1700
Data Index: 4974253 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2057. Min Act: -0.1700
Data Index: 2662595 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2057. Min Act: -0.1700
Data Index: 5315330 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2370. Min Act: -0.1700
Data Index: 7540526 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6745. Min Range: -6.6745
Max Act: 6.2057. Min Act: -0.1700
Data Index: 3878370 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19