Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.6197. Min Act: -0.1700
Data Index: 1303058 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.6197. Min Act: -0.1700
Data Index: 3183191 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.5260. Min Act: -0.1700
Data Index: 5286317 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4867071 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.5260. Min Act: -0.1700
Data Index: 879765 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.5260. Min Act: -0.1700
Data Index: 5234010 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 1651943 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4742195 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 1621727 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 572169 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1244808 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4225336 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.5260. Min Act: -0.1700
Data Index: 5226945 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4225070 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4635. Min Act: -0.1700
Data Index: 2743352 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4947. Min Act: -0.1700
Data Index: 7055352 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4635. Min Act: -0.1700
Data Index: 1760069 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4635. Min Act: -0.1700
Data Index: 1891781 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4635. Min Act: -0.1700
Data Index: 5114594 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6197. Min Range: -4.6197
Max Act: 4.4635. Min Act: -0.1700
Data Index: 700043 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19