Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5371 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.8071. Min Act: -0.1700
Data Index: 8419673 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.6508. Min Act: -0.1700
Data Index: 3021581 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.6196. Min Act: -0.1700
Data Index: 2624226 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.4008. Min Act: -0.1700
Data Index: 5727943 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.3383. Min Act: -0.1700
Data Index: 5471702 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.3383. Min Act: -0.1700
Data Index: 7329919 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.3383. Min Act: -0.1700
Data Index: 1903495 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.2758. Min Act: -0.1700
Data Index: 3226668 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.2446. Min Act: -0.1700
Data Index: 1433388 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.2446. Min Act: -0.1700
Data Index: 4000119 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.1821. Min Act: -0.1700
Data Index: 3774610 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.1508. Min Act: -0.1700
Data Index: 5467198 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.0883. Min Act: -0.1700
Data Index: 8470389 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.0883. Min Act: -0.1700
Data Index: 2913839 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.0571. Min Act: -0.1700
Data Index: 6857296 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8071. Min Range: -7.8071
Max Act: 7.0571. Min Act: -0.1700
Data Index: 4055701 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8071. Min Range: -7.8071
Max Act: 6.9946. Min Act: -0.1700
Data Index: 3385158 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8071. Min Range: -7.8071
Max Act: 6.9633. Min Act: -0.1700
Data Index: 68432 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8071. Min Range: -7.8071
Max Act: 6.9633. Min Act: -0.1700
Data Index: 8565407 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8071. Min Range: -7.8071
Max Act: 6.9633. Min Act: -0.1700
Data Index: 51258 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19