Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2216 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.4004. Min Act: -0.1700
Data Index: 4732008 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.3379. Min Act: -0.1700
Data Index: 8429095 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.3067. Min Act: -0.1700
Data Index: 316727 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.2442. Min Act: -0.1700
Data Index: 104304 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1817. Min Act: -0.1700
Data Index: 3277141 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.2129. Min Act: -0.1700
Data Index: 5724221 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1504. Min Act: -0.1700
Data Index: 5409744 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1504. Min Act: -0.1700
Data Index: 2761526 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1192. Min Act: -0.1700
Data Index: 5782121 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1192. Min Act: -0.1700
Data Index: 2349908 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1192. Min Act: -0.1700
Data Index: 557089 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.1192. Min Act: -0.1700
Data Index: 3711352 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0879. Min Act: -0.1700
Data Index: 4525402 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0567. Min Act: -0.1700
Data Index: 7675573 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0879. Min Act: -0.1700
Data Index: 8055144 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0879. Min Act: -0.1700
Data Index: 2840985 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0879. Min Act: -0.1700
Data Index: 8270886 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0567. Min Act: -0.1700
Data Index: 408585 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0254. Min Act: -0.1700
Data Index: 6287717 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4004. Min Range: -5.4004
Max Act: 5.0567. Min Act: -0.1700
Data Index: 4114996 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19