Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4171 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.4878. Min Act: -0.1700
Data Index: 959336 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.3003. Min Act: -0.1700
Data Index: 3727954 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.2066. Min Act: -0.1700
Data Index: 2976741 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.2378. Min Act: -0.1700
Data Index: 7089964 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.2378. Min Act: -0.1700
Data Index: 3579251 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1753. Min Act: -0.1700
Data Index: 1963310 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.2066. Min Act: -0.1700
Data Index: 6230026 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.2066. Min Act: -0.1700
Data Index: 7066165 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.2066. Min Act: -0.1700
Data Index: 6639217 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1753. Min Act: -0.1700
Data Index: 3285279 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1753. Min Act: -0.1700
Data Index: 814670 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1441. Min Act: -0.1700
Data Index: 3332514 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1441. Min Act: -0.1700
Data Index: 1134169 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1128. Min Act: -0.1700
Data Index: 7942787 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.1128. Min Act: -0.1700
Data Index: 4902057 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.0816. Min Act: -0.1700
Data Index: 1557484 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.0816. Min Act: -0.1700
Data Index: 2326205 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.0816. Min Act: -0.1700
Data Index: 3187142 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.0816. Min Act: -0.1700
Data Index: 6199250 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4878. Min Range: -6.4878
Max Act: 6.0816. Min Act: -0.1700
Data Index: 466717 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19