Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2106. Min Range: -5.2106
Max Act: 5.2106. Min Act: -0.1700
Data Index: 5098424 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2106. Min Range: -5.2106
Max Act: 5.1794. Min Act: -0.1700
Data Index: 84343 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2106. Min Range: -5.2106
Max Act: 5.0856. Min Act: -0.1700
Data Index: 8141813 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.9919. Min Act: -0.1700
Data Index: 7019958 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.9919. Min Act: -0.1700
Data Index: 4704898 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.9294. Min Act: -0.1700
Data Index: 8059599 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.9606. Min Act: -0.1700
Data Index: 3725895 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.9606. Min Act: -0.1700
Data Index: 3995071 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8356. Min Act: -0.1700
Data Index: 6721475 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8669. Min Act: -0.1700
Data Index: 6601707 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8356. Min Act: -0.1700
Data Index: 6035185 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8356. Min Act: -0.1700
Data Index: 8253348 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8669. Min Act: -0.1700
Data Index: 4814655 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8356. Min Act: -0.1700
Data Index: 7863548 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8044. Min Act: -0.1700
Data Index: 7631083 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8044. Min Act: -0.1700
Data Index: 7488306 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8044. Min Act: -0.1694
Data Index: 4549847 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8044. Min Act: -0.1700
Data Index: 796235 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.8044. Min Act: -0.1700
Data Index: 1684200 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2106. Min Range: -5.2106
Max Act: 4.7731. Min Act: -0.1700
Data Index: 2435189 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19