Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.8260. Min Act: -0.1700
Data Index: 8662745 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.7010. Min Act: -0.1700
Data Index: 984557 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.4510. Min Act: -0.1700
Data Index: 780919 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.3573. Min Act: -0.1700
Data Index: 2286890 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.3573. Min Act: -0.1700
Data Index: 884767 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.3260. Min Act: -0.1700
Data Index: 4535709 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2948. Min Act: -0.1700
Data Index: 7329250 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2948. Min Act: -0.1700
Data Index: 1137776 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2323. Min Act: -0.1700
Data Index: 8015093 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2635. Min Act: -0.1700
Data Index: 529278 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2635. Min Act: -0.1700
Data Index: 686108 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2635. Min Act: -0.1700
Data Index: 6604873 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2323. Min Act: -0.1700
Data Index: 5500563 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.2323. Min Act: -0.1700
Data Index: 7918316 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.1385. Min Act: -0.1700
Data Index: 383356 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.1073. Min Act: -0.1700
Data Index: 5826455 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.1385. Min Act: -0.1700
Data Index: 4144260 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.0760. Min Act: -0.1700
Data Index: 2152871 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.1073. Min Act: -0.1700
Data Index: 7889103 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8260. Min Range: -6.8260
Max Act: 6.1073. Min Act: -0.1700
Data Index: 6640456 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19