Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.5296. Min Act: -0.1700
Data Index: 4297457 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.4671. Min Act: -0.1700
Data Index: 4292977 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.3733. Min Act: -0.1700
Data Index: 7101138 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.3108. Min Act: -0.1700
Data Index: 4289816 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.1858. Min Act: -0.1700
Data Index: 6596286 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.1858. Min Act: -0.1700
Data Index: 3766672 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0920. Min Act: -0.1700
Data Index: 7716148 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0920. Min Act: -0.1700
Data Index: 1251066 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0608. Min Act: -0.1700
Data Index: 5889643 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0608. Min Act: -0.1700
Data Index: 4716235 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0608. Min Act: -0.1700
Data Index: 7374989 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0295. Min Act: -0.1700
Data Index: 2023034 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5296. Min Range: -4.5296
Max Act: 3.9983. Min Act: -0.1700
Data Index: 6741201 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0608. Min Act: -0.1700
Data Index: 8541399 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0295. Min Act: -0.1700
Data Index: 7169638 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5296. Min Range: -4.5296
Max Act: 4.0295. Min Act: -0.1700
Data Index: 2837745 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5296. Min Range: -4.5296
Max Act: 3.9670. Min Act: -0.1700
Data Index: 6948645 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5296. Min Range: -4.5296
Max Act: 3.9983. Min Act: -0.1700
Data Index: 4058053 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5296. Min Range: -4.5296
Max Act: 3.9670. Min Act: -0.1700
Data Index: 3509350 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5296. Min Range: -4.5296
Max Act: 3.9670. Min Act: -0.1700
Data Index: 5690007 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19