Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1743. Min Range: -8.1743
Max Act: 8.1743. Min Act: -0.1700
Data Index: 6874858 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.8931. Min Act: -0.1700
Data Index: 5821940 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.8931. Min Act: -0.1700
Data Index: 3185355 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.8931. Min Act: -0.1700
Data Index: 5823318 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.8618. Min Act: -0.1700
Data Index: 6622675 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.7681. Min Act: -0.1700
Data Index: 4529305 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.7368. Min Act: -0.1700
Data Index: 5475334 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.6743. Min Act: -0.1700
Data Index: 1281829 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.6431. Min Act: -0.1700
Data Index: 6072027 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.6743. Min Act: -0.1700
Data Index: 4133478 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.6118. Min Act: -0.1700
Data Index: 4215318 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.5493. Min Act: -0.1700
Data Index: 715598 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.5806. Min Act: -0.1700
Data Index: 4495922 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.5493. Min Act: -0.1700
Data Index: 2660034 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.5181. Min Act: -0.1700
Data Index: 4993932 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.4868. Min Act: -0.1700
Data Index: 5862493 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.4868. Min Act: -0.1700
Data Index: 1328903 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.4868. Min Act: -0.1700
Data Index: 3486033 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.4243. Min Act: -0.1700
Data Index: 7752145 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1743. Min Range: -8.1743
Max Act: 7.4243. Min Act: -0.1700
Data Index: 6092084 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19