Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3764. Min Range: -6.3764
Max Act: 6.3764. Min Act: -0.1700
Data Index: 2322560 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.9076. Min Act: -0.1700
Data Index: 3307473 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.8451. Min Act: -0.1700
Data Index: 5355211 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.8764. Min Act: -0.1700
Data Index: 4575250 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.8139. Min Act: -0.1700
Data Index: 596329 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7826. Min Act: -0.1700
Data Index: 631710 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7826. Min Act: -0.1700
Data Index: 5414655 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7514. Min Act: -0.1700
Data Index: 323963 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7514. Min Act: -0.1700
Data Index: 2437138 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7201. Min Act: -0.1700
Data Index: 8354306 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7201. Min Act: -0.1700
Data Index: 5718177 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.7201. Min Act: -0.1700
Data Index: 7397042 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.6576. Min Act: -0.1700
Data Index: 45751 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.5951. Min Act: -0.1700
Data Index: 2516746 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.6264. Min Act: -0.1700
Data Index: 2865115 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.6576. Min Act: -0.1700
Data Index: 7529999 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6918858 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.5639. Min Act: -0.1700
Data Index: 2955071 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.5639. Min Act: -0.1700
Data Index: 2337682 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3764. Min Range: -6.3764
Max Act: 5.5951. Min Act: -0.1700
Data Index: 2561107 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19