Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.3037. Min Act: -0.1700
Data Index: 8532849 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.2412. Min Act: -0.1700
Data Index: 5401979 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.2412. Min Act: -0.1700
Data Index: 3280532 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.2099. Min Act: -0.1700
Data Index: 6639512 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.2099. Min Act: -0.1700
Data Index: 2946089 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1787. Min Act: -0.1700
Data Index: 1205036 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1474. Min Act: -0.1700
Data Index: 122022 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1474. Min Act: -0.1700
Data Index: 5296722 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1474. Min Act: -0.1700
Data Index: 7715038 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1474. Min Act: -0.1700
Data Index: 97953 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 5127517 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 6153126 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.0849. Min Act: -0.1700
Data Index: 4327844 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 1281739 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 2591343 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 4634247 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 2058612 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 3137407 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 518094 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3037. Min Range: -4.3037
Max Act: 4.1161. Min Act: -0.1700
Data Index: 2352140 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19