Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.1279. Min Act: -0.1700
Data Index: 6040165 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0967. Min Act: -0.1700
Data Index: 1894020 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9404. Min Act: -0.1700
Data Index: 8653180 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9092. Min Act: -0.1700
Data Index: 4658722 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9092. Min Act: -0.1700
Data Index: 7422077 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9404. Min Act: -0.1700
Data Index: 4414022 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.8779. Min Act: -0.1700
Data Index: 2083768 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.8779. Min Act: -0.1700
Data Index: 4283714 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.8467. Min Act: -0.1700
Data Index: 7037544 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.8154. Min Act: -0.1700
Data Index: 494382 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7842. Min Act: -0.1700
Data Index: 7296100 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7842. Min Act: -0.1700
Data Index: 2997075 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7217. Min Act: -0.1700
Data Index: 1931583 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7529. Min Act: -0.1700
Data Index: 5703038 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7529. Min Act: -0.1700
Data Index: 1686397 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7529. Min Act: -0.1700
Data Index: 2338742 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7217. Min Act: -0.1700
Data Index: 1349960 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.7217. Min Act: -0.1700
Data Index: 6795327 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.6592. Min Act: -0.1700
Data Index: 6856884 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.6904. Min Act: -0.1700
Data Index: 3745716 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19