Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2763 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5007. Min Range: -7.5007
Max Act: 7.5007. Min Act: -0.1700
Data Index: 2929431 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5007. Min Range: -7.5007
Max Act: 7.4070. Min Act: -0.1700
Data Index: 8265618 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5007. Min Range: -7.5007
Max Act: 7.1257. Min Act: -0.1700
Data Index: 94040 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5007. Min Range: -7.5007
Max Act: 7.0320. Min Act: -0.1700
Data Index: 59338 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5007. Min Range: -7.5007
Max Act: 7.0007. Min Act: -0.1700
Data Index: 1581431 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.9695. Min Act: -0.1700
Data Index: 8365983 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.9382. Min Act: -0.1700
Data Index: 437700 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.9382. Min Act: -0.1700
Data Index: 3418701 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.9070. Min Act: -0.1700
Data Index: 2171604 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8757. Min Act: -0.1700
Data Index: 6131923 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8757. Min Act: -0.1700
Data Index: 6274254 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8445. Min Act: -0.1700
Data Index: 547496 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8757. Min Act: -0.1700
Data Index: 8245008 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8445. Min Act: -0.1700
Data Index: 7007086 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8445. Min Act: -0.1700
Data Index: 7032243 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8445. Min Act: -0.1700
Data Index: 4297352 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8445. Min Act: -0.1700
Data Index: 4200599 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8132. Min Act: -0.1700
Data Index: 1156431 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8132. Min Act: -0.1700
Data Index: 2428930 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5007. Min Range: -7.5007
Max Act: 6.8132. Min Act: -0.1700
Data Index: 923678 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19