Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.9991. Min Act: -0.1700
Data Index: 2849182 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.8271. Min Act: -0.1700
Data Index: 208717 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.7802. Min Act: -0.1700
Data Index: 7179631 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.7646. Min Act: -0.1700
Data Index: 920149 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.7646. Min Act: -0.1700
Data Index: 1054116 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.7646. Min Act: -0.1700
Data Index: 1829880 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.7802. Min Act: -0.1700
Data Index: 8603968 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.7020. Min Act: -0.1700
Data Index: 50374 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6864. Min Act: -0.1700
Data Index: 1167253 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6551. Min Act: -0.1700
Data Index: 961271 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6394. Min Act: -0.1700
Data Index: 3116467 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6238. Min Act: -0.1700
Data Index: 4596115 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6394. Min Act: -0.1700
Data Index: 2616733 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6081. Min Act: -0.1700
Data Index: 2675572 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.6081. Min Act: -0.1700
Data Index: 2886843 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.5768. Min Act: -0.1700
Data Index: 5593514 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.5925. Min Act: -0.1700
Data Index: 2418839 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.5768. Min Act: -0.1700
Data Index: 691621 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.5768. Min Act: -0.1700
Data Index: 7042132 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9991. Min Range: -3.9991
Max Act: 3.5768. Min Act: -0.1700
Data Index: 68473 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19