Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.7491. Min Act: -0.1700
Data Index: 3874947 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.7179. Min Act: -0.1700
Data Index: 2158188 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.6241. Min Act: -0.1700
Data Index: 7555905 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.5929. Min Act: -0.1700
Data Index: 5804566 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4679. Min Act: -0.1700
Data Index: 2966161 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4679. Min Act: -0.1700
Data Index: 4640943 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4366. Min Act: -0.1700
Data Index: 8135136 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4054. Min Act: -0.1700
Data Index: 4236164 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4366. Min Act: -0.1700
Data Index: 2782599 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3429. Min Act: -0.1700
Data Index: 2387912 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3429. Min Act: -0.1700
Data Index: 8379792 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3116. Min Act: -0.1700
Data Index: 5925060 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.2804. Min Act: -0.1700
Data Index: 3480774 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3116. Min Act: -0.1700
Data Index: 7978373 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3116. Min Act: -0.1700
Data Index: 8373324 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.2804. Min Act: -0.1700
Data Index: 5119100 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.2804. Min Act: -0.1700
Data Index: 5304709 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.2804. Min Act: -0.1700
Data Index: 4894424 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.2804. Min Act: -0.1700
Data Index: 3296932 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.2179. Min Act: -0.1700
Data Index: 8029187 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19