Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3854 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.7054. Min Act: -0.1700
Data Index: 5495051 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.5804. Min Act: -0.1700
Data Index: 5395871 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.5804. Min Act: -0.1700
Data Index: 2881486 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.5804. Min Act: -0.1700
Data Index: 339012 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2991. Min Act: -0.1700
Data Index: 7091531 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2991. Min Act: -0.1700
Data Index: 1274498 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2991. Min Act: -0.1700
Data Index: 3530389 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2679. Min Act: -0.1700
Data Index: 2066783 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2679. Min Act: -0.1700
Data Index: 4764126 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2991. Min Act: -0.1700
Data Index: 6203288 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2991. Min Act: -0.1700
Data Index: 337606 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2679. Min Act: -0.1700
Data Index: 4271611 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2366. Min Act: -0.1700
Data Index: 3016809 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.2366. Min Act: -0.1700
Data Index: 824084 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.1741. Min Act: -0.1700
Data Index: 2968375 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.1741. Min Act: -0.1700
Data Index: 5371733 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.1741. Min Act: -0.1700
Data Index: 6860027 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.1741. Min Act: -0.1700
Data Index: 2085150 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.1429. Min Act: -0.1700
Data Index: 4252082 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7054. Min Range: -6.7054
Max Act: 6.1116. Min Act: -0.1700
Data Index: 6401078 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19