Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1246 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.7479. Min Act: -0.1700
Data Index: 1686883 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.7167. Min Act: -0.1700
Data Index: 1686884 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.7167. Min Act: -0.1700
Data Index: 4269008 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.6542. Min Act: -0.1700
Data Index: 755355 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.6229. Min Act: -0.1700
Data Index: 3248091 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5917. Min Act: -0.1700
Data Index: 1323167 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5917. Min Act: -0.1700
Data Index: 4297253 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5917. Min Act: -0.1700
Data Index: 6937531 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5604. Min Act: -0.1700
Data Index: 8627611 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5604. Min Act: -0.1700
Data Index: 2760874 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5604. Min Act: -0.1700
Data Index: 885447 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5604. Min Act: -0.1700
Data Index: 3869823 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5604. Min Act: -0.1700
Data Index: 1210337 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5292. Min Act: -0.1700
Data Index: 4345065 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.5292. Min Act: -0.1700
Data Index: 5309328 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.4979. Min Act: -0.1700
Data Index: 5886491 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.4979. Min Act: -0.1700
Data Index: 1348832 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.4979. Min Act: -0.1700
Data Index: 4520900 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.4979. Min Act: -0.1700
Data Index: 2643422 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7479. Min Range: -4.7479
Max Act: 4.4979. Min Act: -0.1700
Data Index: 3952099 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19