Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4457 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.9666. Min Act: -0.1700
Data Index: 3374588 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.8716. Min Act: -0.1700
Data Index: 5471721 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.8557. Min Act: -0.1700
Data Index: 8042154 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.8239. Min Act: -0.1700
Data Index: 5715103 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7920. Min Act: -0.1700
Data Index: 7501311 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7761. Min Act: -0.1700
Data Index: 3248199 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7602. Min Act: -0.1700
Data Index: 8301476 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7442. Min Act: -0.1700
Data Index: 7217542 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7442. Min Act: -0.1700
Data Index: 5273922 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 4685354 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7282. Min Act: -0.1700
Data Index: 3247963 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 620064 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 2958378 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 1884444 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 1143103 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 2869097 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.7122. Min Act: -0.1700
Data Index: 2034914 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.6802. Min Act: -0.1700
Data Index: 5852539 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.6802. Min Act: -0.1700
Data Index: 5393679 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9666. Min Range: -2.9666
Max Act: 2.6802. Min Act: -0.1700
Data Index: 1258950 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19