Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.7525. Min Act: -0.1700
Data Index: 5590639 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.6588. Min Act: -0.1700
Data Index: 7762867 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.5963. Min Act: -0.1700
Data Index: 8496131 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.4713. Min Act: -0.1700
Data Index: 5312369 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.4400. Min Act: -0.1700
Data Index: 6358516 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2525. Min Act: -0.1700
Data Index: 953690 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2213. Min Act: -0.1700
Data Index: 4415031 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2213. Min Act: -0.1700
Data Index: 4715239 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1900. Min Act: -0.1700
Data Index: 7220968 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1588. Min Act: -0.1700
Data Index: 2606935 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1275. Min Act: -0.1700
Data Index: 4897697 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1588. Min Act: -0.1700
Data Index: 7823250 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0963. Min Act: -0.1700
Data Index: 7894129 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0650. Min Act: -0.1700
Data Index: 3386022 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0650. Min Act: -0.1700
Data Index: 2303128 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0338. Min Act: -0.1700
Data Index: 5443688 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0025. Min Act: -0.1700
Data Index: 287463 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0025. Min Act: -0.1700
Data Index: 4790432 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7525. Min Range: -6.7525
Max Act: 5.9713. Min Act: -0.1700
Data Index: 5682465 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7525. Min Range: -6.7525
Max Act: 5.9713. Min Act: -0.1700
Data Index: 2611608 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19