Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5998 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1995. Min Range: -6.1995
Max Act: 6.1995. Min Act: -0.1700
Data Index: 527125 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1995. Min Range: -6.1995
Max Act: 6.1370. Min Act: -0.1700
Data Index: 5641624 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.7307. Min Act: -0.1700
Data Index: 6330517 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.6995. Min Act: -0.1700
Data Index: 7273269 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.6682. Min Act: -0.1700
Data Index: 5185474 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.6057. Min Act: -0.1700
Data Index: 720037 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.6057. Min Act: -0.1700
Data Index: 4588185 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.5120. Min Act: -0.1700
Data Index: 8447414 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.5120. Min Act: -0.1700
Data Index: 6715540 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.4495. Min Act: -0.1700
Data Index: 4687868 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.4807. Min Act: -0.1700
Data Index: 1657719 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.4807. Min Act: -0.1700
Data Index: 2720110 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.4495. Min Act: -0.1700
Data Index: 6866433 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.4495. Min Act: -0.1700
Data Index: 4607629 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2671719 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 378331 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 8559049 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 3113137 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.3557. Min Act: -0.1700
Data Index: 7597548 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1995. Min Range: -6.1995
Max Act: 5.3557. Min Act: -0.1700
Data Index: 3806961 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19