Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.7124. Min Act: -0.1700
Data Index: 1012273 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.4624. Min Act: -0.1700
Data Index: 3558569 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.4936. Min Act: -0.1700
Data Index: 8744259 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.4311. Min Act: -0.1700
Data Index: 6450260 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.3686. Min Act: -0.1700
Data Index: 4986474 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.3686. Min Act: -0.1700
Data Index: 683299 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.3686. Min Act: -0.1700
Data Index: 5135621 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.3374. Min Act: -0.1700
Data Index: 1604666 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2749. Min Act: -0.1700
Data Index: 4115715 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2749. Min Act: -0.1700
Data Index: 1845168 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2749. Min Act: -0.1700
Data Index: 1020864 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2749. Min Act: -0.1700
Data Index: 2709420 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2436. Min Act: -0.1700
Data Index: 653402 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2749. Min Act: -0.1700
Data Index: 4760946 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2436. Min Act: -0.1700
Data Index: 4858874 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2436. Min Act: -0.1700
Data Index: 7392501 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2749. Min Act: -0.1700
Data Index: 4082070 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2124. Min Act: -0.1700
Data Index: 4245683 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2124. Min Act: -0.1700
Data Index: 865313 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7124. Min Range: -5.7124
Max Act: 5.2436. Min Act: -0.1700
Data Index: 5234507 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19