Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 592 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.8752. Min Act: -0.1700
Data Index: 1890238 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.7502. Min Act: -0.1700
Data Index: 2282408 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6564. Min Act: -0.1700
Data Index: 1447814 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6564. Min Act: -0.1700
Data Index: 517269 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.6564. Min Act: -0.1700
Data Index: 1738474 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5939. Min Act: -0.1700
Data Index: 1536051 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5939. Min Act: -0.1700
Data Index: 5164477 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5314. Min Act: -0.1700
Data Index: 374394 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5314. Min Act: -0.1700
Data Index: 217415 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5314. Min Act: -0.1700
Data Index: 6454037 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5314. Min Act: -0.1700
Data Index: 3069806 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5002. Min Act: -0.1700
Data Index: 3943307 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5002. Min Act: -0.1700
Data Index: 2563726 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5002. Min Act: -0.1700
Data Index: 5683078 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5002. Min Act: -0.1700
Data Index: 7445043 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.5002. Min Act: -0.1700
Data Index: 3980672 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.4377. Min Act: -0.1700
Data Index: 2325676 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.4064. Min Act: -0.1700
Data Index: 3836560 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.4689. Min Act: -0.1700
Data Index: 2658354 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8752. Min Range: -4.8752
Max Act: 4.4689. Min Act: -0.1700
Data Index: 5829701 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19