Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.6950. Min Act: -0.1700
Data Index: 2224016 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.2888. Min Act: -0.1700
Data Index: 5163022 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4251813 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.2888. Min Act: -0.1700
Data Index: 5355210 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.2575. Min Act: -0.1700
Data Index: 7298833 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1950. Min Act: -0.1700
Data Index: 7209777 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.2263. Min Act: -0.1700
Data Index: 189487 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.2263. Min Act: -0.1700
Data Index: 1323389 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1950. Min Act: -0.1700
Data Index: 4672315 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1950. Min Act: -0.1700
Data Index: 3374519 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1638. Min Act: -0.1700
Data Index: 1015046 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1638. Min Act: -0.1700
Data Index: 1594050 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1638. Min Act: -0.1700
Data Index: 5159527 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1950. Min Act: -0.1700
Data Index: 8676107 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1638. Min Act: -0.1700
Data Index: 220483 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1325. Min Act: -0.1700
Data Index: 2652689 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1013. Min Act: -0.1700
Data Index: 4986701 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1325. Min Act: -0.1700
Data Index: 5395022 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1013. Min Act: -0.1700
Data Index: 3798350 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.1013. Min Act: -0.1700
Data Index: 2535646 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19