Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.7181. Min Act: -0.1700
Data Index: 139209 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.5931. Min Act: -0.1700
Data Index: 1296093 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.5931. Min Act: -0.1700
Data Index: 3934944 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.5931. Min Act: -0.1700
Data Index: 3451318 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.5618. Min Act: -0.1700
Data Index: 2254371 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4993. Min Act: -0.1700
Data Index: 192024 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4993. Min Act: -0.1700
Data Index: 2049307 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4681. Min Act: -0.1700
Data Index: 6190176 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4368. Min Act: -0.1700
Data Index: 728977 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4056. Min Act: -0.1700
Data Index: 2981018 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3431. Min Act: -0.1700
Data Index: 7912108 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3743. Min Act: -0.1700
Data Index: 691533 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3743. Min Act: -0.1700
Data Index: 50141 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3743. Min Act: -0.1700
Data Index: 7600356 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3743. Min Act: -0.1700
Data Index: 2035596 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3431. Min Act: -0.1700
Data Index: 2851042 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3743. Min Act: -0.1700
Data Index: 6775524 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3431. Min Act: -0.1700
Data Index: 1693151 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3431. Min Act: -0.1700
Data Index: 1487501 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3431. Min Act: -0.1700
Data Index: 395849 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19