Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0586. Min Range: -3.0586
Max Act: 3.0429. Min Act: -0.1700
Data Index: 5493830 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0586. Min Range: -3.0586
Max Act: 3.0586. Min Act: -0.1700
Data Index: 7999139 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0586. Min Range: -3.0586
Max Act: 3.0271. Min Act: -0.1700
Data Index: 7999138 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0586. Min Range: -3.0586
Max Act: 3.0271. Min Act: -0.1700
Data Index: 7999137 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0586. Min Range: -3.0586
Max Act: 3.0113. Min Act: -0.1700
Data Index: 2800295 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0586. Min Range: -3.0586
Max Act: 3.0113. Min Act: -0.1700
Data Index: 2800301 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9638. Min Act: -0.1700
Data Index: 7763806 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9638. Min Act: -0.1700
Data Index: 7999136 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9480. Min Act: -0.1700
Data Index: 2800298 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9322. Min Act: -0.1700
Data Index: 5799818 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9638. Min Act: -0.1700
Data Index: 2800299 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9163. Min Act: -0.1700
Data Index: 7999134 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9163. Min Act: -0.1700
Data Index: 5915502 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9163. Min Act: -0.1700
Data Index: 7999141 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9480. Min Act: -0.1700
Data Index: 2800300 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2800294 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.8846. Min Act: -0.1700
Data Index: 3319848 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.9005. Min Act: -0.1700
Data Index: 2800297 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.8846. Min Act: -0.1700
Data Index: 8190230 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0586. Min Range: -3.0586
Max Act: 2.8688. Min Act: -0.1700
Data Index: 560819 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19