Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.1102. Min Act: -0.1700
Data Index: 1137761 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0944. Min Act: -0.1700
Data Index: 3386047 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0944. Min Act: -0.1700
Data Index: 1211737 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0629. Min Act: -0.1700
Data Index: 2157443 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0471. Min Act: -0.1700
Data Index: 601729 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0313. Min Act: -0.1700
Data Index: 3134234 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0629. Min Act: -0.1700
Data Index: 1194533 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0313. Min Act: -0.1700
Data Index: 6923927 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0155. Min Act: -0.1700
Data Index: 7169405 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9997. Min Act: -0.1700
Data Index: 6628518 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9839. Min Act: -0.1700
Data Index: 7333820 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1102. Min Range: -3.1102
Max Act: 3.0313. Min Act: -0.1700
Data Index: 2465138 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9839. Min Act: -0.1700
Data Index: 8084913 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9523. Min Act: -0.1700
Data Index: 4047445 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9839. Min Act: -0.1700
Data Index: 3448541 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9997. Min Act: -0.1700
Data Index: 6252578 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9523. Min Act: -0.1700
Data Index: 1010775 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9681. Min Act: -0.1700
Data Index: 8087804 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9681. Min Act: -0.1700
Data Index: 8305397 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1102. Min Range: -3.1102
Max Act: 2.9523. Min Act: -0.1700
Data Index: 4611910 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19