Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1313 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0064. Min Range: -8.0064
Max Act: 8.0064. Min Act: -0.1700
Data Index: 813107 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.6939. Min Act: -0.1700
Data Index: 7636797 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5689. Min Act: -0.1700
Data Index: 1652717 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5689. Min Act: -0.1700
Data Index: 6435521 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5689. Min Act: -0.1700
Data Index: 1071004 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5689. Min Act: -0.1700
Data Index: 3637795 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5689. Min Act: -0.1700
Data Index: 1306450 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5064. Min Act: -0.1700
Data Index: 894516 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5064. Min Act: -0.1700
Data Index: 933289 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5064. Min Act: -0.1700
Data Index: 6497165 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.5689. Min Act: -0.1700
Data Index: 5208999 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 7807456 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.4439. Min Act: -0.1700
Data Index: 5934186 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.4439. Min Act: -0.1700
Data Index: 4194025 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 4648387 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 1745866 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 281300 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 6963004 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 5481361 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0064. Min Range: -8.0064
Max Act: 7.3814. Min Act: -0.1700
Data Index: 724495 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19