Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.4654. Min Act: -0.1700
Data Index: 4533925 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.4184. Min Act: -0.1700
Data Index: 749790 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.4027. Min Act: -0.1700
Data Index: 5554003 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.3713. Min Act: -0.1700
Data Index: 5489190 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.3557. Min Act: -0.1700
Data Index: 1370025 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.3400. Min Act: -0.1700
Data Index: 1987724 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.3400. Min Act: -0.1700
Data Index: 179065 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.3243. Min Act: -0.1700
Data Index: 1102811 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.3243. Min Act: -0.1700
Data Index: 1435313 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2929. Min Act: -0.1700
Data Index: 7139969 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2772. Min Act: -0.1700
Data Index: 2184856 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2615. Min Act: -0.1700
Data Index: 424094 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2615. Min Act: -0.1700
Data Index: 3088950 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2772. Min Act: -0.1700
Data Index: 4305366 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2458. Min Act: -0.1700
Data Index: 5996260 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2458. Min Act: -0.1700
Data Index: 7227608 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2458. Min Act: -0.1700
Data Index: 6944875 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2300. Min Act: -0.1700
Data Index: 6410300 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2143. Min Act: -0.1700
Data Index: 3016807 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4654. Min Range: -3.4654
Max Act: 3.2143. Min Act: -0.1700
Data Index: 6455760 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19