Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 465 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1294. Min Range: -4.1294
Max Act: 4.1294. Min Act: -0.1700
Data Index: 305882 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1294. Min Range: -4.1294
Max Act: 4.0981. Min Act: -0.1700
Data Index: 3579610 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1294. Min Range: -4.1294
Max Act: 4.0043. Min Act: -0.1700
Data Index: 3465134 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.9418. Min Act: -0.1700
Data Index: 3923306 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.9106. Min Act: -0.1700
Data Index: 385160 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.9418. Min Act: -0.1700
Data Index: 3831836 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.8480. Min Act: -0.1700
Data Index: 477493 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.8480. Min Act: -0.1700
Data Index: 3029659 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.8167. Min Act: -0.1700
Data Index: 2067612 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.8167. Min Act: -0.1700
Data Index: 2164970 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7855. Min Act: -0.1700
Data Index: 6154864 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7698. Min Act: -0.1700
Data Index: 4121532 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7855. Min Act: -0.1700
Data Index: 1308554 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7698. Min Act: -0.1700
Data Index: 997377 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7698. Min Act: -0.1700
Data Index: 4716157 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7855. Min Act: -0.1700
Data Index: 1545964 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7386. Min Act: -0.1700
Data Index: 5416375 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7542. Min Act: -0.1700
Data Index: 7167833 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7698. Min Act: -0.1700
Data Index: 2854834 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1294. Min Range: -4.1294
Max Act: 3.7542. Min Act: -0.1700
Data Index: 5848459 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19