Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1191 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.3489. Min Act: -0.1700
Data Index: 6020145 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.1131. Min Act: -0.1700
Data Index: 1212206 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0659. Min Act: -0.1700
Data Index: 3265158 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0501. Min Act: -0.1700
Data Index: 1165598 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0185. Min Act: -0.1700
Data Index: 4169751 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0185. Min Act: -0.1700
Data Index: 1006408 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0027. Min Act: -0.1700
Data Index: 2862234 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0185. Min Act: -0.1700
Data Index: 1450725 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3489. Min Range: -3.3489
Max Act: 3.0027. Min Act: -0.1700
Data Index: 1340989 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9869. Min Act: -0.1700
Data Index: 7145137 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9711. Min Act: -0.1700
Data Index: 6889179 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9711. Min Act: -0.1700
Data Index: 2761186 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9553. Min Act: -0.1700
Data Index: 6799596 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9553. Min Act: -0.1700
Data Index: 2287384 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9553. Min Act: -0.1700
Data Index: 3481110 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9394. Min Act: -0.1700
Data Index: 6931629 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9394. Min Act: -0.1700
Data Index: 5708291 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9236. Min Act: -0.1700
Data Index: 432673 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9077. Min Act: -0.1700
Data Index: 336853 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3489. Min Range: -3.3489
Max Act: 2.9077. Min Act: -0.1700
Data Index: 4675806 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19