Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.5232. Min Act: -0.1700
Data Index: 6794886 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.3670. Min Act: -0.1700
Data Index: 1610113 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2732. Min Act: -0.1700
Data Index: 1806109 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2732. Min Act: -0.1700
Data Index: 5106691 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2420. Min Act: -0.1700
Data Index: 1610111 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2420. Min Act: -0.1700
Data Index: 8184268 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2107. Min Act: -0.1700
Data Index: 6233873 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2107. Min Act: -0.1700
Data Index: 4246308 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.2107. Min Act: -0.1700
Data Index: 8717081 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1795. Min Act: -0.1700
Data Index: 6582743 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1795. Min Act: -0.1700
Data Index: 1610112 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1795. Min Act: -0.1700
Data Index: 8309150 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1795. Min Act: -0.1700
Data Index: 8615348 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6568834 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6109006 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1170. Min Act: -0.1700
Data Index: 6909060 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1482. Min Act: -0.1700
Data Index: 5706773 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1482. Min Act: -0.1700
Data Index: 8157738 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1482. Min Act: -0.1700
Data Index: 7994174 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5232. Min Range: -5.5232
Max Act: 5.1170. Min Act: -0.1700
Data Index: 4857949 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19