Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.7464. Min Act: -0.1700
Data Index: 758926 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.4964. Min Act: -0.1700
Data Index: 325391 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.3714. Min Act: -0.1700
Data Index: 2969219 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.4027. Min Act: -0.1700
Data Index: 8237456 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.3089. Min Act: -0.1700
Data Index: 3975293 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.3089. Min Act: -0.1700
Data Index: 2000466 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.2777. Min Act: -0.1700
Data Index: 6764069 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.3089. Min Act: -0.1700
Data Index: 5826668 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.2464. Min Act: -0.1700
Data Index: 6707974 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1839. Min Act: -0.1700
Data Index: 5957226 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.2152. Min Act: -0.1700
Data Index: 6355242 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1839. Min Act: -0.1700
Data Index: 3520877 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1839. Min Act: -0.1700
Data Index: 1777615 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1526. Min Act: -0.1700
Data Index: 2671283 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1214. Min Act: -0.1700
Data Index: 639712 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1526. Min Act: -0.1700
Data Index: 5875195 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.0901. Min Act: -0.1700
Data Index: 6282762 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.1214. Min Act: -0.1700
Data Index: 3368330 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.0901. Min Act: -0.1700
Data Index: 7582731 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7464. Min Range: -4.7464
Max Act: 4.0901. Min Act: -0.1700
Data Index: 934341 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19