Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 277 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2904. Min Range: -7.2904
Max Act: 7.2904. Min Act: -0.1700
Data Index: 7594917 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2904. Min Range: -7.2904
Max Act: 7.1029. Min Act: -0.1700
Data Index: 1327800 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2904. Min Range: -7.2904
Max Act: 7.0717. Min Act: -0.1700
Data Index: 3191322 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2904. Min Range: -7.2904
Max Act: 7.0404. Min Act: -0.1700
Data Index: 1054773 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.9154. Min Act: -0.1700
Data Index: 3004770 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.9467. Min Act: -0.1700
Data Index: 565661 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8842. Min Act: -0.1700
Data Index: 7141305 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8529. Min Act: -0.1700
Data Index: 7022801 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8842. Min Act: -0.1700
Data Index: 2239228 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8217. Min Act: -0.1700
Data Index: 5498328 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8529. Min Act: -0.1700
Data Index: 6981038 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8217. Min Act: -0.1700
Data Index: 3949786 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.8217. Min Act: -0.1700
Data Index: 7477355 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.7592. Min Act: -0.1700
Data Index: 3637788 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.7592. Min Act: -0.1700
Data Index: 1108149 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.7592. Min Act: -0.1700
Data Index: 8699410 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.7279. Min Act: -0.1700
Data Index: 6611122 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.6967. Min Act: -0.1700
Data Index: 7695883 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.7279. Min Act: -0.1700
Data Index: 7215871 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2904. Min Range: -7.2904
Max Act: 6.7592. Min Act: -0.1700
Data Index: 538805 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19