Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1805. Min Range: -6.1805
Max Act: 6.1805. Min Act: -0.1700
Data Index: 483177 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1805. Min Range: -6.1805
Max Act: 6.0868. Min Act: -0.1700
Data Index: 3241065 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1805. Min Range: -6.1805
Max Act: 6.0868. Min Act: -0.1700
Data Index: 3205234 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1805. Min Range: -6.1805
Max Act: 6.0243. Min Act: -0.1700
Data Index: 4378931 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.9930. Min Act: -0.1700
Data Index: 869289 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.9930. Min Act: -0.1700
Data Index: 4870620 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.9930. Min Act: -0.1700
Data Index: 342414 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.9618. Min Act: -0.1700
Data Index: 8319182 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8993. Min Act: -0.1700
Data Index: 4232563 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.9305. Min Act: -0.1700
Data Index: 842105 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8680. Min Act: -0.1700
Data Index: 8652640 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8680. Min Act: -0.1700
Data Index: 6205638 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8368. Min Act: -0.1700
Data Index: 5547112 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8368. Min Act: -0.1700
Data Index: 8512869 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8368. Min Act: -0.1700
Data Index: 2561704 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.8055. Min Act: -0.1700
Data Index: 3039963 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.7743. Min Act: -0.1700
Data Index: 2557675 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.7743. Min Act: -0.1700
Data Index: 2745354 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.7743. Min Act: -0.1700
Data Index: 8543569 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1805. Min Range: -6.1805
Max Act: 5.7743. Min Act: -0.1700
Data Index: 6751100 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19