Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.8260. Min Act: -0.1700
Data Index: 7803411 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.5135. Min Act: -0.1700
Data Index: 1484353 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.4510. Min Act: -0.1700
Data Index: 6636459 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.4510. Min Act: -0.1700
Data Index: 3881346 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.4510. Min Act: -0.1700
Data Index: 4768225 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.2635. Min Act: -0.1700
Data Index: 5694890 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.1385. Min Act: -0.1700
Data Index: 7669325 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.2010. Min Act: -0.1700
Data Index: 3530019 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.0760. Min Act: -0.1700
Data Index: 7073537 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8260. Min Range: -9.8260
Max Act: 9.0760. Min Act: -0.1700
Data Index: 290204 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.9510. Min Act: -0.1700
Data Index: 480634 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.8885. Min Act: -0.1700
Data Index: 2446273 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.9510. Min Act: -0.1700
Data Index: 7042278 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.8885. Min Act: -0.1700
Data Index: 2237348 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.8260. Min Act: -0.1700
Data Index: 5037354 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.8260. Min Act: -0.1700
Data Index: 8468799 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.8260. Min Act: -0.1700
Data Index: 448094 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.7010. Min Act: -0.1700
Data Index: 2918990 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.7635. Min Act: -0.1700
Data Index: 8671497 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8260. Min Range: -9.8260
Max Act: 8.6385. Min Act: -0.1700
Data Index: 2382599 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19