Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.8093. Min Act: -0.1700
Data Index: 5011173 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.6218. Min Act: -0.1700
Data Index: 8675628 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5593. Min Act: -0.1700
Data Index: 8610605 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5905. Min Act: -0.1700
Data Index: 1862588 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5198736 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5385453 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5905. Min Act: -0.1700
Data Index: 3985191 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.5280. Min Act: -0.1700
Data Index: 2111290 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.4968. Min Act: -0.1700
Data Index: 7306939 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.4655. Min Act: -0.1700
Data Index: 4081008 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.4968. Min Act: -0.1700
Data Index: 6487907 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.4968. Min Act: -0.1700
Data Index: 1556419 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.4968. Min Act: -0.1700
Data Index: 2786586 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3405. Min Act: -0.1700
Data Index: 3977388 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3718. Min Act: -0.1700
Data Index: 8070886 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3718. Min Act: -0.1700
Data Index: 7463949 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3405. Min Act: -0.1700
Data Index: 7048370 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3405. Min Act: -0.1700
Data Index: 2830006 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3093. Min Act: -0.1700
Data Index: 6120798 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8093. Min Range: -4.8093
Max Act: 4.3405. Min Act: -0.1700
Data Index: 5137163 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19