Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 32
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: 8606204 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.5929. Min Act: -0.1700
Data Index: 6973257 (Open Web Text)
Max Activating Token Index: 556
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: 7737012 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.6241. Min Act: -0.1700
Data Index: 5720633 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.5929. Min Act: -0.1700
Data Index: 2343843 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4991. Min Act: -0.1700
Data Index: 1158888 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4991. Min Act: -0.1700
Data Index: 8273853 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.5304. Min Act: -0.1700
Data Index: 3739177 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4679. Min Act: -0.1700
Data Index: 8082768 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4366. Min Act: -0.1700
Data Index: 6990692 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4366. Min Act: -0.1700
Data Index: 4465013 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4366. Min Act: -0.1700
Data Index: 2096266 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4054. Min Act: -0.1700
Data Index: 4811504 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.4054. Min Act: -0.1700
Data Index: 2829566 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3741. Min Act: -0.1700
Data Index: 4383580 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3741. Min Act: -0.1700
Data Index: 2204390 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3741. Min Act: -0.1700
Data Index: 559578 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3741. Min Act: -0.1700
Data Index: 3532055 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3741. Min Act: -0.1700
Data Index: 327097 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7491. Min Range: -5.7491
Max Act: 5.3429. Min Act: -0.1700
Data Index: 7835821 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19