Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.3534. Min Act: -0.1700
Data Index: 3183089 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.2284. Min Act: -0.1700
Data Index: 7070425 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.1971. Min Act: -0.1700
Data Index: 2946248 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0409. Min Act: -0.1700
Data Index: 2048464 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0409. Min Act: -0.1700
Data Index: 4336147 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0409. Min Act: -0.1700
Data Index: 8486412 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0409. Min Act: -0.1700
Data Index: 3819646 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0096. Min Act: -0.1700
Data Index: 3886618 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0096. Min Act: -0.1700
Data Index: 7555247 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9784. Min Act: -0.1700
Data Index: 5547685 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9784. Min Act: -0.1700
Data Index: 3876195 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9784. Min Act: -0.1700
Data Index: 3715316 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0096. Min Act: -0.1700
Data Index: 8811255 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0096. Min Act: -0.1700
Data Index: 465118 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9471. Min Act: -0.1700
Data Index: 2867236 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9471. Min Act: -0.1700
Data Index: 8573208 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9471. Min Act: -0.1700
Data Index: 2738210 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9784. Min Act: -0.1700
Data Index: 1108091 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9471. Min Act: -0.1700
Data Index: 3065889 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9159. Min Act: -0.1700
Data Index: 4934327 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19