Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1975 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3997. Min Range: -10.3997
Max Act: 10.3997. Min Act: -0.1700
Data Index: 2699660 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3997. Min Range: -10.3997
Max Act: 10.2122. Min Act: -0.1700
Data Index: 4319081 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3997. Min Range: -10.3997
Max Act: 10.1497. Min Act: -0.1700
Data Index: 6621613 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3997. Min Range: -10.3997
Max Act: 10.1497. Min Act: -0.1700
Data Index: 3979517 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.9622. Min Act: -0.1700
Data Index: 8304520 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3997. Min Range: -10.3997
Max Act: 10.0247. Min Act: -0.1700
Data Index: 7059337 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.8997. Min Act: -0.1700
Data Index: 6810354 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.8997. Min Act: -0.1700
Data Index: 5441962 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.8372. Min Act: -0.1700
Data Index: 3510051 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.8372. Min Act: -0.1700
Data Index: 1544607 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.8997. Min Act: -0.1700
Data Index: 1401855 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.7747. Min Act: -0.1700
Data Index: 2334181 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.7122. Min Act: -0.1700
Data Index: 3930801 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.7122. Min Act: -0.1700
Data Index: 2251176 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.6497. Min Act: -0.1700
Data Index: 7728597 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.7122. Min Act: -0.1700
Data Index: 953229 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.5872. Min Act: -0.1700
Data Index: 245339 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.5872. Min Act: -0.1700
Data Index: 148757 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.6497. Min Act: -0.1700
Data Index: 8792212 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3997. Min Range: -10.3997
Max Act: 9.5872. Min Act: -0.1700
Data Index: 4855882 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19