Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.3215. Min Act: -0.1700
Data Index: 8035970 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.2590. Min Act: -0.1700
Data Index: 869853 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.2278. Min Act: -0.1700
Data Index: 5577157 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.2278. Min Act: -0.1700
Data Index: 1293701 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1965. Min Act: -0.1700
Data Index: 3956962 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1965. Min Act: -0.1700
Data Index: 2491820 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1340. Min Act: -0.1700
Data Index: 1271168 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1653. Min Act: -0.1700
Data Index: 1305553 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1653. Min Act: -0.1700
Data Index: 5935148 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1340. Min Act: -0.1700
Data Index: 4606195 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1028. Min Act: -0.1700
Data Index: 1956729 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1028. Min Act: -0.1700
Data Index: 8484925 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.1028. Min Act: -0.1700
Data Index: 8249634 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.0715. Min Act: -0.1700
Data Index: 7682923 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.0403. Min Act: -0.1700
Data Index: 6134253 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.0090. Min Act: -0.1700
Data Index: 1250233 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3215. Min Range: -5.3215
Max Act: 5.0090. Min Act: -0.1700
Data Index: 2093523 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3215. Min Range: -5.3215
Max Act: 4.9778. Min Act: -0.1700
Data Index: 1459476 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3215. Min Range: -5.3215
Max Act: 4.8840. Min Act: -0.1700
Data Index: 5453179 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3215. Min Range: -5.3215
Max Act: 4.8840. Min Act: -0.1700
Data Index: 5182006 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19