Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5130 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.8672. Min Act: -0.1700
Data Index: 4009923 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.8359. Min Act: -0.1700
Data Index: 7657607 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.8359. Min Act: -0.1700
Data Index: 8629655 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.8359. Min Act: -0.1700
Data Index: 8805378 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.7734. Min Act: -0.1700
Data Index: 2903559 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.7734. Min Act: -0.1700
Data Index: 1937478 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.8047. Min Act: -0.1700
Data Index: 1635050 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.6172. Min Act: -0.1700
Data Index: 3363231 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.5859. Min Act: -0.1700
Data Index: 1107463 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.5234. Min Act: -0.1700
Data Index: 6658530 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4922. Min Act: -0.1700
Data Index: 3546051 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4922. Min Act: -0.1700
Data Index: 4536930 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4609. Min Act: -0.1700
Data Index: 502794 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4922. Min Act: -0.1700
Data Index: 4550724 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4609. Min Act: -0.1700
Data Index: 8658289 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4609. Min Act: -0.1700
Data Index: 2727009 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4297. Min Act: -0.1700
Data Index: 6732783 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.4297. Min Act: -0.1700
Data Index: 2322825 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.3984. Min Act: -0.1700
Data Index: 1719390 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8672. Min Range: -7.8672
Max Act: 7.3984. Min Act: -0.1700
Data Index: 3707180 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19