Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4330. Min Range: -7.4330
Max Act: 7.4330. Min Act: -0.1700
Data Index: 7076883 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4330. Min Range: -7.4330
Max Act: 7.2768. Min Act: -0.1700
Data Index: 3734123 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4330. Min Range: -7.4330
Max Act: 7.1205. Min Act: -0.1700
Data Index: 7343364 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4330. Min Range: -7.4330
Max Act: 7.1518. Min Act: -0.1700
Data Index: 2075607 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4330. Min Range: -7.4330
Max Act: 7.0893. Min Act: -0.1700
Data Index: 4722239 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4330. Min Range: -7.4330
Max Act: 7.0893. Min Act: -0.1700
Data Index: 8760945 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9643. Min Act: -0.1700
Data Index: 6104930 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9018. Min Act: -0.1700
Data Index: 5686879 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9330. Min Act: -0.1700
Data Index: 2111519 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9018. Min Act: -0.1700
Data Index: 1087871 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9018. Min Act: -0.1700
Data Index: 8299101 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9018. Min Act: -0.1700
Data Index: 5702899 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9018. Min Act: -0.1700
Data Index: 3261129 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.9018. Min Act: -0.1700
Data Index: 5039607 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.8080. Min Act: -0.1700
Data Index: 2264247 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.8393. Min Act: -0.1699
Data Index: 5296587 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.8080. Min Act: -0.1700
Data Index: 6666285 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.7455. Min Act: -0.1700
Data Index: 711000 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.7143. Min Act: -0.1700
Data Index: 3485409 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4330. Min Range: -7.4330
Max Act: 6.7455. Min Act: -0.1700
Data Index: 1199802 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19