Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.6743. Min Act: -0.1700
Data Index: 1899713 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.5493. Min Act: -0.1700
Data Index: 1045008 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.4868. Min Act: -0.1700
Data Index: 1836252 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.4243. Min Act: -0.1700
Data Index: 960349 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.2993. Min Act: -0.1700
Data Index: 6851402 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.1743. Min Act: -0.1700
Data Index: 4444682 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.1743. Min Act: -0.1700
Data Index: 1723101 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.1118. Min Act: -0.1698
Data Index: 5824416 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.1118. Min Act: -0.1700
Data Index: 3384207 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.0493. Min Act: -0.1700
Data Index: 3657010 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6743. Min Range: -11.6743
Max Act: 11.0493. Min Act: -0.1700
Data Index: 5569337 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9868. Min Act: -0.1700
Data Index: 6800423 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9243. Min Act: -0.1700
Data Index: 7865817 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9243. Min Act: -0.1700
Data Index: 925518 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.8618. Min Act: -0.1700
Data Index: 4851990 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9243. Min Act: -0.1700
Data Index: 256146 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9243. Min Act: -0.1700
Data Index: 276787 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9243. Min Act: -0.1700
Data Index: 4016759 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.9243. Min Act: -0.1700
Data Index: 1616366 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6743. Min Range: -11.6743
Max Act: 10.8618. Min Act: -0.1700
Data Index: 960350 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19