Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3846 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.9989. Min Act: -0.1700
Data Index: 6138047 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.9364. Min Act: -0.1700
Data Index: 2290694 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.7801. Min Act: -0.1700
Data Index: 4254715 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.7489. Min Act: -0.1700
Data Index: 990812 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.6864. Min Act: -0.1700
Data Index: 2520427 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.6864. Min Act: -0.1700
Data Index: 3756183 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.6864. Min Act: -0.1700
Data Index: 1324264 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.6551. Min Act: -0.1700
Data Index: 7839956 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.6239. Min Act: -0.1700
Data Index: 537374 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.5926. Min Act: -0.1700
Data Index: 8328215 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.5614. Min Act: -0.1700
Data Index: 5921416 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.4051. Min Act: -0.1700
Data Index: 25715 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.4051. Min Act: -0.1700
Data Index: 7305435 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3739. Min Act: -0.1700
Data Index: 1671228 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3426. Min Act: -0.1700
Data Index: 4214827 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3739. Min Act: -0.1700
Data Index: 7704453 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3739. Min Act: -0.1700
Data Index: 1647573 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3426. Min Act: -0.1700
Data Index: 2792888 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3114. Min Act: -0.1700
Data Index: 1082619 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9989. Min Range: -6.9989
Max Act: 6.3114. Min Act: -0.1700
Data Index: 4412363 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19