Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.2330. Min Act: -0.1700
Data Index: 5499849 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.1080. Min Act: -0.1700
Data Index: 2366592 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.1080. Min Act: -0.1700
Data Index: 8636253 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.1080. Min Act: -0.1700
Data Index: 2476839 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.1080. Min Act: -0.1700
Data Index: 3468871 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.0455. Min Act: -0.1700
Data Index: 2773505 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.0455. Min Act: -0.1700
Data Index: 654002 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.0455. Min Act: -0.1700
Data Index: 4019068 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.0455. Min Act: -0.1700
Data Index: 7073252 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.0455. Min Act: -0.1700
Data Index: 548462 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9830. Min Act: -0.1700
Data Index: 2509239 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9830. Min Act: -0.1700
Data Index: 5684242 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2330. Min Range: -7.2330
Max Act: 7.0455. Min Act: -0.1700
Data Index: 8450989 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9830. Min Act: -0.1700
Data Index: 4547300 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9205. Min Act: -0.1700
Data Index: 343083 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9205. Min Act: -0.1699
Data Index: 4553662 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9205. Min Act: -0.1700
Data Index: 1457352 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9205. Min Act: -0.1700
Data Index: 3097613 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9205. Min Act: -0.1700
Data Index: 4725531 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2330. Min Range: -7.2330
Max Act: 6.9205. Min Act: -0.1698
Data Index: 271727 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19