Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.8939. Min Act: -0.1700
Data Index: 974558 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.8001. Min Act: -0.1700
Data Index: 948619 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.7689. Min Act: -0.1700
Data Index: 4456556 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.6439. Min Act: -0.1700
Data Index: 3393174 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.5501. Min Act: -0.1700
Data Index: 5259577 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.5501. Min Act: -0.1700
Data Index: 8090549 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.5501. Min Act: -0.1700
Data Index: 1607274 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.5189. Min Act: -0.1700
Data Index: 8008712 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.4564. Min Act: -0.1700
Data Index: 8822415 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.4564. Min Act: -0.1700
Data Index: 3111543 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.3626. Min Act: -0.1700
Data Index: 3606050 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.3314. Min Act: -0.1700
Data Index: 441467 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.3001. Min Act: -0.1700
Data Index: 693808 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.2689. Min Act: -0.1700
Data Index: 3132247 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.2689. Min Act: -0.1700
Data Index: 1518405 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.3001. Min Act: -0.1700
Data Index: 519035 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.2376. Min Act: -0.1700
Data Index: 6910789 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.2064. Min Act: -0.1700
Data Index: 1014867 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.2064. Min Act: -0.1700
Data Index: 8470690 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8939. Min Range: -5.8939
Max Act: 5.2064. Min Act: -0.1700
Data Index: 6743210 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19