Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0940. Min Range: -6.0940
Max Act: 6.0940. Min Act: -0.1700
Data Index: 2197588 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0940. Min Range: -6.0940
Max Act: 6.0002. Min Act: -0.1700
Data Index: 3933685 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.9065. Min Act: -0.1700
Data Index: 5501266 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.9065. Min Act: -0.1700
Data Index: 3669494 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.8752. Min Act: -0.1700
Data Index: 7452039 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.8752. Min Act: -0.1700
Data Index: 3390794 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7815. Min Act: -0.1700
Data Index: 761499 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7502. Min Act: -0.1700
Data Index: 3085029 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7502. Min Act: -0.1700
Data Index: 920201 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7502. Min Act: -0.1700
Data Index: 529913 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7502. Min Act: -0.1700
Data Index: 2494821 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7190. Min Act: -0.1700
Data Index: 4811528 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7190. Min Act: -0.1700
Data Index: 2553975 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.6877. Min Act: -0.1700
Data Index: 3384267 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.6877. Min Act: -0.1700
Data Index: 8774542 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7190. Min Act: -0.1700
Data Index: 4313933 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.7190. Min Act: -0.1700
Data Index: 6066210 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.6565. Min Act: -0.1700
Data Index: 6464246 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.6565. Min Act: -0.1700
Data Index: 3375776 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0940. Min Range: -6.0940
Max Act: 5.6565. Min Act: -0.1700
Data Index: 2303120 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19