Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.8975. Min Range: -9.8975
Max Act: 9.8975. Min Act: -0.1700
Data Index: 6239293 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8975. Min Range: -9.8975
Max Act: 9.2100. Min Act: -0.1700
Data Index: 6239291 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.9600. Min Act: -0.1700
Data Index: 6239292 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.9600. Min Act: -0.1700
Data Index: 4537570 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.9600. Min Act: -0.1700
Data Index: 3218565 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.9600. Min Act: -0.1698
Data Index: 155107 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.9600. Min Act: -0.1700
Data Index: 4296470 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.8350. Min Act: -0.1700
Data Index: 5591963 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.8350. Min Act: -0.1700
Data Index: 4165886 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7725. Min Act: -0.1700
Data Index: 2278006 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7725. Min Act: -0.1700
Data Index: 4165893 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7100. Min Act: -0.1700
Data Index: 1146276 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7100. Min Act: -0.1700
Data Index: 2206222 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7100. Min Act: -0.1700
Data Index: 6243013 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7100. Min Act: -0.1699
Data Index: 5026841 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.7100. Min Act: -0.1700
Data Index: 3620335 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.6475. Min Act: -0.1700
Data Index: 7036067 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.6475. Min Act: -0.1700
Data Index: 8254113 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.6475. Min Act: -0.1700
Data Index: 8644449 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8975. Min Range: -9.8975
Max Act: 8.6475. Min Act: -0.1700
Data Index: 155109 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19