Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.9388. Min Act: -0.1700
Data Index: 8760572 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.9388. Min Act: -0.1700
Data Index: 6631659 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.8919. Min Act: -0.1700
Data Index: 1628272 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.8137. Min Act: -0.1700
Data Index: 1719007 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.7668. Min Act: -0.1700
Data Index: 2954713 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.7355. Min Act: -0.1700
Data Index: 4300395 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.7199. Min Act: -0.1700
Data Index: 1034881 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.7042. Min Act: -0.1700
Data Index: 631373 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.7199. Min Act: -0.1700
Data Index: 7986191 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6886. Min Act: -0.1700
Data Index: 1034880 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.7042. Min Act: -0.1700
Data Index: 6247307 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6886. Min Act: -0.1700
Data Index: 3197999 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 7066797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 520104 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 2878362 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 6017221 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 7323451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 7217622 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 2902081 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9388. Min Range: -3.9388
Max Act: 3.6729. Min Act: -0.1700
Data Index: 2902084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19