Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6648. Min Act: -0.1700
Data Index: 6827648 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6648. Min Act: -0.1700
Data Index: 4371892 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6487. Min Act: -0.1700
Data Index: 8308969 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6487. Min Act: -0.1700
Data Index: 2565869 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6327. Min Act: -0.1700
Data Index: 6827651 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6166. Min Act: -0.1700
Data Index: 1683988 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6005. Min Act: -0.1700
Data Index: 6827650 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6327. Min Act: -0.1700
Data Index: 8105787 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6327. Min Act: -0.1700
Data Index: 911200 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6327. Min Act: -0.1700
Data Index: 6336354 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6487. Min Act: -0.1700
Data Index: 7747803 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6005. Min Act: -0.1700
Data Index: 8443624 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.6005. Min Act: -0.1700
Data Index: 6856659 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5844. Min Act: -0.1700
Data Index: 8287025 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5844. Min Act: -0.1700
Data Index: 6436420 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5683. Min Act: -0.1700
Data Index: 65201 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5844. Min Act: -0.1700
Data Index: 2422281 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5522. Min Act: -0.1700
Data Index: 6261334 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5683. Min Act: -0.1700
Data Index: 782065 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6648. Min Range: -2.6648
Max Act: 2.5522. Min Act: -0.1700
Data Index: 1501588 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19