Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1331. Min Range: -6.1331
Max Act: 6.1331. Min Act: -0.1700
Data Index: 4189018 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1331. Min Range: -6.1331
Max Act: 6.0393. Min Act: -0.1700
Data Index: 3129677 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1331. Min Range: -6.1331
Max Act: 6.0393. Min Act: -0.1700
Data Index: 5444516 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.9768. Min Act: -0.1700
Data Index: 3040480 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.9143. Min Act: -0.1700
Data Index: 1793438 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.8831. Min Act: -0.1700
Data Index: 5238046 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.7893. Min Act: -0.1700
Data Index: 2090612 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.7268. Min Act: -0.1700
Data Index: 8349415 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6956. Min Act: -0.1700
Data Index: 8506906 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6956. Min Act: -0.1700
Data Index: 8321869 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6643. Min Act: -0.1700
Data Index: 6841315 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6018. Min Act: -0.1700
Data Index: 8420621 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6331. Min Act: -0.1700
Data Index: 2779097 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6956. Min Act: -0.1700
Data Index: 5090731 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6331. Min Act: -0.1700
Data Index: 2154310 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6331. Min Act: -0.1700
Data Index: 4385720 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6331. Min Act: -0.1700
Data Index: 5477939 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6331. Min Act: -0.1700
Data Index: 8573958 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6018. Min Act: -0.1700
Data Index: 195308 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1331. Min Range: -6.1331
Max Act: 5.6018. Min Act: -0.1700
Data Index: 8202388 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19