Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5447 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.9089. Min Act: -0.1700
Data Index: 7513248 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.6587. Min Act: -0.1700
Data Index: 5135597 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.6430. Min Act: -0.1700
Data Index: 8275104 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.6430. Min Act: -0.1700
Data Index: 5710265 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.6587. Min Act: -0.1700
Data Index: 3231674 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.6117. Min Act: -0.1700
Data Index: 3104900 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.6117. Min Act: -0.1700
Data Index: 5545520 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5961. Min Act: -0.1700
Data Index: 2022312 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5648. Min Act: -0.1700
Data Index: 2543387 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5648. Min Act: -0.1700
Data Index: 7676459 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5491. Min Act: -0.1700
Data Index: 5055638 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5178. Min Act: -0.1700
Data Index: 6208680 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5022. Min Act: -0.1700
Data Index: 4125399 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.4865. Min Act: -0.1700
Data Index: 6477889 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.4865. Min Act: -0.1700
Data Index: 5118038 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.5022. Min Act: -0.1700
Data Index: 4296229 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.4395. Min Act: -0.1700
Data Index: 2732804 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.4395. Min Act: -0.1700
Data Index: 7061278 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.4081. Min Act: -0.1700
Data Index: 7046415 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9089. Min Range: -3.9089
Max Act: 3.4238. Min Act: -0.1700
Data Index: 699159 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19