Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.9758. Min Act: -0.1700
Data Index: 2555131 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0070. Min Range: -8.0070
Max Act: 8.0070. Min Act: -0.1700
Data Index: 1929568 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.9445. Min Act: -0.1700
Data Index: 7295003 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.9133. Min Act: -0.1700
Data Index: 1713244 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.8508. Min Act: -0.1700
Data Index: 3877301 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.7883. Min Act: -0.1700
Data Index: 7729292 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.7258. Min Act: -0.1700
Data Index: 5630817 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.6945. Min Act: -0.1700
Data Index: 691356 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.6633. Min Act: -0.1700
Data Index: 941739 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.6008. Min Act: -0.1700
Data Index: 1165055 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.5695. Min Act: -0.1700
Data Index: 113658 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.5383. Min Act: -0.1700
Data Index: 8441843 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4758. Min Act: -0.1700
Data Index: 7652376 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4758. Min Act: -0.1700
Data Index: 107170 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4758. Min Act: -0.1700
Data Index: 850215 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4758. Min Act: -0.1700
Data Index: 1688755 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4445. Min Act: -0.1700
Data Index: 5509526 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4445. Min Act: -0.1700
Data Index: 4982491 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4445. Min Act: -0.1700
Data Index: 971852 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0070. Min Range: -8.0070
Max Act: 7.4445. Min Act: -0.1700
Data Index: 4142959 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19