Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2208 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1420. Min Range: -10.1420
Max Act: 10.1420. Min Act: -0.1700
Data Index: 3395124 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1420. Min Range: -10.1420
Max Act: 9.3295. Min Act: -0.1700
Data Index: 1166009 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1420. Min Range: -10.1420
Max Act: 9.0170. Min Act: -0.1700
Data Index: 8100196 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1420. Min Range: -10.1420
Max Act: 9.0170. Min Act: -0.1700
Data Index: 530958 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.6420. Min Act: -0.1700
Data Index: 6953743 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.5795. Min Act: -0.1700
Data Index: 8170052 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.5170. Min Act: -0.1700
Data Index: 4193619 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.2670. Min Act: -0.1700
Data Index: 655682 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.2045. Min Act: -0.1700
Data Index: 2763003 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1420. Min Range: -10.1420
Max Act: 7.8295. Min Act: -0.1700
Data Index: 6455704 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.2045. Min Act: -0.1700
Data Index: 7689870 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1420. Min Range: -10.1420
Max Act: 7.7670. Min Act: -0.1700
Data Index: 6056341 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1420. Min Range: -10.1420
Max Act: 7.7670. Min Act: -0.1700
Data Index: 6552068 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.0795. Min Act: -0.1700
Data Index: 7798399 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1420. Min Range: -10.1420
Max Act: 5.2982. Min Act: -0.1700
Data Index: 8270441 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.0170. Min Act: -0.1700
Data Index: 4884435 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1420. Min Range: -10.1420
Max Act: 8.2670. Min Act: -0.1700
Data Index: 5322010 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1420. Min Range: -10.1420
Max Act: 7.6107. Min Act: -0.1700
Data Index: 6189646 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1420. Min Range: -10.1420
Max Act: 7.9545. Min Act: -0.1700
Data Index: 4936009 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1420. Min Range: -10.1420
Max Act: 7.9545. Min Act: -0.1700
Data Index: 4167583 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19