Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2468 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.5760. Min Act: -0.1700
Data Index: 335094 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.5760. Min Act: -0.1700
Data Index: 6819672 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.3885. Min Act: -0.1700
Data Index: 5907382 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.4510. Min Act: -0.1700
Data Index: 2718809 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.4510. Min Act: -0.1700
Data Index: 5092683 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.3260. Min Act: -0.1700
Data Index: 1692667 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.3260. Min Act: -0.1700
Data Index: 5337106 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.2010. Min Act: -0.1700
Data Index: 602872 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.2010. Min Act: -0.1700
Data Index: 5396942 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.1385. Min Act: -0.1700
Data Index: 2515554 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.2010. Min Act: -0.1700
Data Index: 7609905 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.1073. Min Act: -0.1700
Data Index: 2951182 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.1073. Min Act: -0.1700
Data Index: 3724019 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.0448. Min Act: -0.1700
Data Index: 5534545 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.0760. Min Act: -0.1700
Data Index: 1635886 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.0760. Min Act: -0.1700
Data Index: 4294482 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5760. Min Range: -8.5760
Max Act: 8.0135. Min Act: -0.1700
Data Index: 3755049 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5760. Min Range: -8.5760
Max Act: 7.9510. Min Act: -0.1700
Data Index: 426438 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5760. Min Range: -8.5760
Max Act: 7.9510. Min Act: -0.1700
Data Index: 889170 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5760. Min Range: -8.5760
Max Act: 7.9198. Min Act: -0.1700
Data Index: 901150 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19