Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.1806. Min Act: -0.1700
Data Index: 7085342 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.1181. Min Act: -0.1700
Data Index: 5445418 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1806. Min Range: -4.1806
Max Act: 4.0243. Min Act: -0.1700
Data Index: 7054858 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9618. Min Act: -0.1700
Data Index: 3780348 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1176545 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.9305. Min Act: -0.1700
Data Index: 5164991 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8993. Min Act: -0.1700
Data Index: 421952 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8680. Min Act: -0.1700
Data Index: 604334 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8680. Min Act: -0.1700
Data Index: 7464717 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8367. Min Act: -0.1700
Data Index: 3692512 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8054. Min Act: -0.1700
Data Index: 6569911 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8054. Min Act: -0.1700
Data Index: 3713548 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8054. Min Act: -0.1700
Data Index: 250065 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.8054. Min Act: -0.1700
Data Index: 3359185 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.7585. Min Act: -0.1700
Data Index: 1060328 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2611908 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.7742. Min Act: -0.1700
Data Index: 6891501 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.7742. Min Act: -0.1700
Data Index: 3829938 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2118985 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1806. Min Range: -4.1806
Max Act: 3.7585. Min Act: -0.1700
Data Index: 2086336 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19