Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0887. Min Range: -4.0887
Max Act: 4.0887. Min Act: -0.1700
Data Index: 867757 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.9949. Min Act: -0.1700
Data Index: 210146 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4820759 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.9324. Min Act: -0.1700
Data Index: 6536622 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8073. Min Act: -0.1700
Data Index: 570047 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8386. Min Act: -0.1700
Data Index: 6346648 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8386. Min Act: -0.1700
Data Index: 7114382 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8386. Min Act: -0.1700
Data Index: 2523941 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8386. Min Act: -0.1700
Data Index: 3939439 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8073. Min Act: -0.1700
Data Index: 4374999 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7760. Min Act: -0.1700
Data Index: 4957920 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.8073. Min Act: -0.1700
Data Index: 7543785 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7134. Min Act: -0.1700
Data Index: 6739768 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7134. Min Act: -0.1700
Data Index: 731915 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7447. Min Act: -0.1700
Data Index: 2348245 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7760. Min Act: -0.1700
Data Index: 5976226 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7447. Min Act: -0.1700
Data Index: 3522450 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7134. Min Act: -0.1700
Data Index: 3284744 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.6822. Min Act: -0.1700
Data Index: 319665 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0887. Min Range: -4.0887
Max Act: 3.7447. Min Act: -0.1700
Data Index: 7085794 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19