Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1003 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.7902. Min Act: -0.1700
Data Index: 6091620 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.6652. Min Act: -0.1700
Data Index: 7637341 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.6339. Min Act: -0.1700
Data Index: 8333247 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.6027. Min Act: -0.1700
Data Index: 3687174 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.6027. Min Act: -0.1700
Data Index: 3781726 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.5714. Min Act: -0.1700
Data Index: 1513640 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.5714. Min Act: -0.1700
Data Index: 5040825 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.4464. Min Act: -0.1700
Data Index: 1612124 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3839. Min Act: -0.1700
Data Index: 7311601 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.4464. Min Act: -0.1700
Data Index: 3773498 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.4152. Min Act: -0.1700
Data Index: 3498943 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3527. Min Act: -0.1700
Data Index: 732660 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3839. Min Act: -0.1700
Data Index: 5147193 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.4152. Min Act: -0.1700
Data Index: 7311602 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3839. Min Act: -0.1700
Data Index: 5884185 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3527. Min Act: -0.1700
Data Index: 6361055 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3214. Min Act: -0.1700
Data Index: 5984169 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.3527. Min Act: -0.1700
Data Index: 8682410 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.2589. Min Act: -0.1700
Data Index: 2455083 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7902. Min Range: -5.7902
Max Act: 5.2902. Min Act: -0.1700
Data Index: 3687173 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19