Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1528. Min Range: -3.1528
Max Act: 3.1528. Min Act: -0.1700
Data Index: 7648065 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1528. Min Range: -3.1528
Max Act: 3.0425. Min Act: -0.1700
Data Index: 8817982 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9951. Min Act: -0.1700
Data Index: 7740225 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9793. Min Act: -0.1700
Data Index: 2690709 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9635. Min Act: -0.1700
Data Index: 33773 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9318. Min Act: -0.1700
Data Index: 2041765 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9160. Min Act: -0.1700
Data Index: 974719 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9160. Min Act: -0.1700
Data Index: 633792 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.9160. Min Act: -0.1700
Data Index: 3112305 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.8843. Min Act: -0.1700
Data Index: 6824293 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.8684. Min Act: -0.1700
Data Index: 3225467 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.8366. Min Act: -0.1700
Data Index: 4363649 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.8048. Min Act: -0.1700
Data Index: 1523132 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7889. Min Act: -0.1700
Data Index: 6321090 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7889. Min Act: -0.1700
Data Index: 6211021 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7889. Min Act: -0.1700
Data Index: 8577788 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7729. Min Act: -0.1700
Data Index: 876547 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7570. Min Act: -0.1700
Data Index: 663043 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7729. Min Act: -0.1700
Data Index: 7459819 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1528. Min Range: -3.1528
Max Act: 2.7570. Min Act: -0.1700
Data Index: 5424251 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19