Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5458 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.3077. Min Act: -0.1700
Data Index: 3630025 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.2920. Min Act: -0.1700
Data Index: 850651 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.2606. Min Act: -0.1700
Data Index: 3629857 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.2135. Min Act: -0.1700
Data Index: 3190046 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.2135. Min Act: -0.1700
Data Index: 2867215 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1978. Min Act: -0.1700
Data Index: 1650279 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1820. Min Act: -0.1700
Data Index: 2840709 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1820. Min Act: -0.1700
Data Index: 7423707 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1506. Min Act: -0.1700
Data Index: 2546241 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1348. Min Act: -0.1700
Data Index: 5106233 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1506. Min Act: -0.1700
Data Index: 724145 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1348. Min Act: -0.1700
Data Index: 3263395 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1348. Min Act: -0.1700
Data Index: 3847883 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.0875. Min Act: -0.1700
Data Index: 4283843 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1033. Min Act: -0.1700
Data Index: 4549330 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1033. Min Act: -0.1700
Data Index: 2299006 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1033. Min Act: -0.1700
Data Index: 2121488 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1033. Min Act: -0.1700
Data Index: 996066 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.0875. Min Act: -0.1700
Data Index: 4415649 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3077. Min Range: -3.3077
Max Act: 3.1033. Min Act: -0.1700
Data Index: 4502865 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19