Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2614 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0427. Min Range: -5.0427
Max Act: 5.0427. Min Act: -0.1700
Data Index: 3497799 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.9802. Min Act: -0.1700
Data Index: 2215885 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.9802. Min Act: -0.1700
Data Index: 1076474 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.9802. Min Act: -0.1700
Data Index: 1770355 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.9489. Min Act: -0.1700
Data Index: 3239971 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.8864. Min Act: -0.1700
Data Index: 1861313 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.8552. Min Act: -0.1700
Data Index: 1618950 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4679721 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.8239. Min Act: -0.1700
Data Index: 4677042 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1900816 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4135420 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4031516 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7927. Min Act: -0.1700
Data Index: 3924382 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7302. Min Act: -0.1700
Data Index: 4625439 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.6989. Min Act: -0.1700
Data Index: 3577306 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.7614. Min Act: -0.1700
Data Index: 4209847 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.6677. Min Act: -0.1700
Data Index: 7136901 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.6989. Min Act: -0.1700
Data Index: 7669532 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.6989. Min Act: -0.1700
Data Index: 6553808 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0427. Min Range: -5.0427
Max Act: 4.6989. Min Act: -0.1700
Data Index: 2524792 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19