Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4243 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0679. Min Act: -0.1700
Data Index: 6657333 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8491. Min Act: -0.1700
Data Index: 6042024 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8491. Min Act: -0.1700
Data Index: 8407775 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8178. Min Act: -0.1700
Data Index: 704002 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7553. Min Act: -0.1700
Data Index: 5421142 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7553. Min Act: -0.1700
Data Index: 8096700 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7553. Min Act: -0.1700
Data Index: 6491740 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7553. Min Act: -0.1700
Data Index: 3483471 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7553. Min Act: -0.1700
Data Index: 6432574 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7396. Min Act: -0.1700
Data Index: 5789926 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7240. Min Act: -0.1700
Data Index: 6915015 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7083. Min Act: -0.1700
Data Index: 8455056 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7240. Min Act: -0.1700
Data Index: 4515502 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6927. Min Act: -0.1700
Data Index: 779198 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6614. Min Act: -0.1700
Data Index: 2877235 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6614. Min Act: -0.1700
Data Index: 570303 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6614. Min Act: -0.1700
Data Index: 6607351 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6301. Min Act: -0.1700
Data Index: 5169529 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6458. Min Act: -0.1700
Data Index: 957818 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6145. Min Act: -0.1700
Data Index: 1764231 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19