Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0975. Min Range: -7.0975
Max Act: 7.0975. Min Act: -0.1700
Data Index: 5294841 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.9725. Min Act: -0.1700
Data Index: 2438372 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.9412. Min Act: -0.1700
Data Index: 4354439 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.8162. Min Act: -0.1700
Data Index: 1511985 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.7537. Min Act: -0.1700
Data Index: 3545938 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.7225. Min Act: -0.1700
Data Index: 7248883 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.7537. Min Act: -0.1700
Data Index: 7835028 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.7225. Min Act: -0.1700
Data Index: 2473358 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.6912. Min Act: -0.1700
Data Index: 4498863 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5662. Min Act: -0.1700
Data Index: 8721519 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5662. Min Act: -0.1700
Data Index: 7264236 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5662. Min Act: -0.1700
Data Index: 4199003 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5350. Min Act: -0.1700
Data Index: 2512203 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5350. Min Act: -0.1700
Data Index: 2895768 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5037. Min Act: -0.1700
Data Index: 3601247 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5037. Min Act: -0.1700
Data Index: 4215060 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5037. Min Act: -0.1700
Data Index: 8525105 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.5037. Min Act: -0.1700
Data Index: 6274073 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.4725. Min Act: -0.1700
Data Index: 6047811 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0975. Min Range: -7.0975
Max Act: 6.4725. Min Act: -0.1700
Data Index: 3233464 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19