Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 437 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0982. Min Range: -5.0982
Max Act: 5.0982. Min Act: -0.1700
Data Index: 3879768 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.9420. Min Act: -0.1700
Data Index: 7836152 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.8795. Min Act: -0.1700
Data Index: 1031093 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.6295. Min Act: -0.1700
Data Index: 3501487 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.5670. Min Act: -0.1700
Data Index: 3708510 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.5670. Min Act: -0.1700
Data Index: 25361 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.4732. Min Act: -0.1700
Data Index: 3747418 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.5045. Min Act: -0.1700
Data Index: 7010055 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.4420. Min Act: -0.1700
Data Index: 4979153 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.4107. Min Act: -0.1700
Data Index: 7525380 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.4107. Min Act: -0.1700
Data Index: 2003548 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.4107. Min Act: -0.1700
Data Index: 3879769 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3795. Min Act: -0.1700
Data Index: 6495169 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3795. Min Act: -0.1700
Data Index: 8621090 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3795. Min Act: -0.1700
Data Index: 7525381 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3795. Min Act: -0.1700
Data Index: 3286742 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.4107. Min Act: -0.1700
Data Index: 2432119 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3482. Min Act: -0.1700
Data Index: 3024333 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3482. Min Act: -0.1700
Data Index: 8470964 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0982. Min Range: -5.0982
Max Act: 4.3482. Min Act: -0.1700
Data Index: 6138172 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19