Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0496. Min Range: -6.0496
Max Act: 6.0496. Min Act: -0.1700
Data Index: 8161713 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.9246. Min Act: -0.1700
Data Index: 8476115 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.8308. Min Act: -0.1700
Data Index: 71551 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.7996. Min Act: -0.1700
Data Index: 2691248 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.7683. Min Act: -0.1700
Data Index: 7552623 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.7683. Min Act: -0.1700
Data Index: 7238840 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.7371. Min Act: -0.1700
Data Index: 4972321 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.7058. Min Act: -0.1700
Data Index: 3575618 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6746. Min Act: -0.1700
Data Index: 3703929 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6746. Min Act: -0.1700
Data Index: 522204 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6746. Min Act: -0.1700
Data Index: 1165918 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6433. Min Act: -0.1700
Data Index: 6480488 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6433. Min Act: -0.1700
Data Index: 5242247 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6433. Min Act: -0.1700
Data Index: 6195585 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6433. Min Act: -0.1700
Data Index: 478764 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6433. Min Act: -0.1700
Data Index: 1364576 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6121. Min Act: -0.1700
Data Index: 4789856 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6121. Min Act: -0.1700
Data Index: 7238849 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6121. Min Act: -0.1700
Data Index: 3293388 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0496. Min Range: -6.0496
Max Act: 5.6121. Min Act: -0.1700
Data Index: 6380499 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19