Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.8003. Min Act: -0.1700
Data Index: 4927598 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.7691. Min Act: -0.1700
Data Index: 1802583 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.8003. Min Act: -0.1700
Data Index: 8815920 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.7066. Min Act: -0.1700
Data Index: 3893895 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.7066. Min Act: -0.1700
Data Index: 1845745 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6753. Min Act: -0.1700
Data Index: 5249621 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6753. Min Act: -0.1700
Data Index: 5367183 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6753. Min Act: -0.1700
Data Index: 1688270 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6128. Min Act: -0.1700
Data Index: 2077111 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6128. Min Act: -0.1700
Data Index: 8105429 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6128. Min Act: -0.1700
Data Index: 3840917 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6128. Min Act: -0.1700
Data Index: 7641319 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6128. Min Act: -0.1700
Data Index: 605531 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.5816. Min Act: -0.1700
Data Index: 3179394 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.5816. Min Act: -0.1700
Data Index: 1588529 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.5816. Min Act: -0.1700
Data Index: 7085873 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.5503. Min Act: -0.1700
Data Index: 7360810 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.6128. Min Act: -0.1700
Data Index: 177525 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.5816. Min Act: -0.1700
Data Index: 5137017 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8003. Min Range: -4.8003
Max Act: 4.5503. Min Act: -0.1700
Data Index: 2188141 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19