Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 82 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.9522. Min Act: -0.1700
Data Index: 7665470 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.9522. Min Act: -0.1700
Data Index: 5259433 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.9053. Min Act: -0.1700
Data Index: 6437524 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.9210. Min Act: -0.1700
Data Index: 7151924 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.8897. Min Act: -0.1700
Data Index: 5108210 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.8115. Min Act: -0.1700
Data Index: 125629 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.7802. Min Act: -0.1700
Data Index: 1098739 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6864. Min Act: -0.1700
Data Index: 7400711 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.7020. Min Act: -0.1700
Data Index: 5179953 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.7020. Min Act: -0.1700
Data Index: 7561343 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6708. Min Act: -0.1700
Data Index: 1007912 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6864. Min Act: -0.1700
Data Index: 4374740 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6708. Min Act: -0.1700
Data Index: 3255731 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6864. Min Act: -0.1700
Data Index: 1024220 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6551. Min Act: -0.1700
Data Index: 8644322 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6551. Min Act: -0.1700
Data Index: 2997771 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6238. Min Act: -0.1700
Data Index: 1774649 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6551. Min Act: -0.1700
Data Index: 1085529 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6082. Min Act: -0.1700
Data Index: 3096249 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9522. Min Range: -3.9522
Max Act: 3.6082. Min Act: -0.1700
Data Index: 6908303 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19