Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.7974. Min Act: -0.1700
Data Index: 25564 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.4536. Min Act: -0.1700
Data Index: 7983956 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.2661. Min Act: -0.1700
Data Index: 5890245 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.2661. Min Act: -0.1700
Data Index: 901972 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.2349. Min Act: -0.1700
Data Index: 5096076 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.1724. Min Act: -0.1700
Data Index: 4254385 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.1724. Min Act: -0.1700
Data Index: 3882285 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.1411. Min Act: -0.1700
Data Index: 4254386 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.1099. Min Act: -0.1700
Data Index: 4576115 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.0786. Min Act: -0.1700
Data Index: 8749171 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.0161. Min Act: -0.1700
Data Index: 1515639 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7974. Min Range: -6.7974
Max Act: 6.0161. Min Act: -0.1700
Data Index: 5491951 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 4351473 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 501438 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.9536. Min Act: -0.1700
Data Index: 8478549 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.9536. Min Act: -0.1700
Data Index: 822245 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 1045391 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3871021 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.8911. Min Act: -0.1700
Data Index: 4857104 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7974. Min Range: -6.7974
Max Act: 5.8911. Min Act: -0.1699
Data Index: 2960700 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19