Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1923 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3046. Min Range: -6.3046
Max Act: 6.3046. Min Act: -0.1700
Data Index: 5082847 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.8046. Min Act: -0.1700
Data Index: 5779696 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.7108. Min Act: -0.1700
Data Index: 3229775 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.6796. Min Act: -0.1700
Data Index: 1571172 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.6796. Min Act: -0.1700
Data Index: 787665 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.6171. Min Act: -0.1700
Data Index: 7008639 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.6483. Min Act: -0.1700
Data Index: 3589863 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5546. Min Act: -0.1700
Data Index: 8034735 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.6171. Min Act: -0.1700
Data Index: 4271835 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5858. Min Act: -0.1700
Data Index: 216252 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5858. Min Act: -0.1700
Data Index: 1629611 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5233. Min Act: -0.1700
Data Index: 916325 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5233. Min Act: -0.1700
Data Index: 7099517 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.4921. Min Act: -0.1700
Data Index: 4098235 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5233. Min Act: -0.1700
Data Index: 7787125 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5546. Min Act: -0.1700
Data Index: 2257118 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5233. Min Act: -0.1700
Data Index: 500633 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.4608. Min Act: -0.1700
Data Index: 47239 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.4921. Min Act: -0.1700
Data Index: 7132856 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3046. Min Range: -6.3046
Max Act: 5.5233. Min Act: -0.1700
Data Index: 6917837 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19