Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.3728. Min Act: -0.1700
Data Index: 7837833 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.3571. Min Act: -0.1700
Data Index: 3466085 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.2472. Min Act: -0.1700
Data Index: 5536942 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.2315. Min Act: -0.1700
Data Index: 3095589 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.2001. Min Act: -0.1700
Data Index: 4269209 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1843. Min Act: -0.1700
Data Index: 145876 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1843. Min Act: -0.1700
Data Index: 6724792 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1371. Min Act: -0.1700
Data Index: 5165945 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1371. Min Act: -0.1700
Data Index: 2013856 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1371. Min Act: -0.1700
Data Index: 1429025 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1371. Min Act: -0.1700
Data Index: 459216 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1371. Min Act: -0.1700
Data Index: 8349951 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1214. Min Act: -0.1700
Data Index: 5016826 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1214. Min Act: -0.1700
Data Index: 638608 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1056. Min Act: -0.1700
Data Index: 3932519 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1056. Min Act: -0.1700
Data Index: 5600325 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.0899. Min Act: -0.1700
Data Index: 5042771 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.0899. Min Act: -0.1700
Data Index: 4652916 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.1056. Min Act: -0.1700
Data Index: 6803330 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3728. Min Range: -3.3728
Max Act: 3.0899. Min Act: -0.1700
Data Index: 4248300 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19