Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.9388. Min Act: -0.1700
Data Index: 3050016 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.8763. Min Act: -0.1700
Data Index: 2644063 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.7513. Min Act: -0.1700
Data Index: 95656 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.8138. Min Act: -0.1700
Data Index: 857558 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.7513. Min Act: -0.1700
Data Index: 6023239 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.6888. Min Act: -0.1700
Data Index: 4529162 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.6263. Min Act: -0.1700
Data Index: 4720364 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.6263. Min Act: -0.1700
Data Index: 2367886 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.5638. Min Act: -0.1700
Data Index: 4112736 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.5638. Min Act: -0.1700
Data Index: 4247433 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.5013. Min Act: -0.1700
Data Index: 1473979 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.5013. Min Act: -0.1700
Data Index: 814372 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.4388. Min Act: -0.1700
Data Index: 4320220 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.4388. Min Act: -0.1700
Data Index: 411102 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.3763. Min Act: -0.1700
Data Index: 317799 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.3763. Min Act: -0.1700
Data Index: 6146002 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.3763. Min Act: -0.1700
Data Index: 2747175 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.3138. Min Act: -0.1700
Data Index: 3491948 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.3138. Min Act: -0.1700
Data Index: 4448958 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9388. Min Range: -9.9388
Max Act: 9.2513. Min Act: -0.1700
Data Index: 4320222 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19