Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.3892. Min Act: -0.1700
Data Index: 4737418 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.2642. Min Act: -0.1700
Data Index: 5163967 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1704. Min Act: -0.1700
Data Index: 2090184 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1392. Min Act: -0.1700
Data Index: 4922833 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1704. Min Act: -0.1700
Data Index: 969352 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1392. Min Act: -0.1700
Data Index: 6822481 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1392. Min Act: -0.1700
Data Index: 6822480 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1392. Min Act: -0.1700
Data Index: 4949538 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5223562 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0767. Min Act: -0.1700
Data Index: 250506 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0767. Min Act: -0.1700
Data Index: 7551267 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0142. Min Act: -0.1700
Data Index: 5176428 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0142. Min Act: -0.1700
Data Index: 4813776 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3892. Min Range: -6.3892
Max Act: 6.0142. Min Act: -0.1700
Data Index: 7551257 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3892. Min Range: -6.3892
Max Act: 5.9829. Min Act: -0.1700
Data Index: 4311499 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3892. Min Range: -6.3892
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3508920 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3892. Min Range: -6.3892
Max Act: 5.9829. Min Act: -0.1700
Data Index: 6859064 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3892. Min Range: -6.3892
Max Act: 5.9829. Min Act: -0.1700
Data Index: 5235771 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3892. Min Range: -6.3892
Max Act: 5.9829. Min Act: -0.1700
Data Index: 2861011 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3892. Min Range: -6.3892
Max Act: 5.9829. Min Act: -0.1700
Data Index: 1604681 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19