Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.3479. Min Act: -0.1700
Data Index: 2288237 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.3167. Min Act: -0.1700
Data Index: 834127 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.3167. Min Act: -0.1700
Data Index: 8797366 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.1917. Min Act: -0.1700
Data Index: 8207959 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.2229. Min Act: -0.1700
Data Index: 3251591 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.0979. Min Act: -0.1700
Data Index: 2637061 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.0667. Min Act: -0.1700
Data Index: 3383925 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3479. Min Range: -6.3479
Max Act: 6.0354. Min Act: -0.1700
Data Index: 3675320 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.9729. Min Act: -0.1700
Data Index: 6705982 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.9729. Min Act: -0.1700
Data Index: 3919230 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.9104. Min Act: -0.1700
Data Index: 7764170 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.9104. Min Act: -0.1700
Data Index: 920562 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.9104. Min Act: -0.1700
Data Index: 7210138 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.9104. Min Act: -0.1700
Data Index: 4056081 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.8792. Min Act: -0.1700
Data Index: 8451221 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.8792. Min Act: -0.1700
Data Index: 8374408 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.8792. Min Act: -0.1699
Data Index: 3643448 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.8479. Min Act: -0.1700
Data Index: 5561245 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.8792. Min Act: -0.1700
Data Index: 4241701 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3479. Min Range: -6.3479
Max Act: 5.8167. Min Act: -0.1700
Data Index: 2230368 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19