Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 493 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.3843. Min Act: -0.1700
Data Index: 3522298 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.2280. Min Act: -0.1700
Data Index: 2674703 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1968. Min Act: -0.1700
Data Index: 8110542 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1968. Min Act: -0.1700
Data Index: 1676870 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1655. Min Act: -0.1700
Data Index: 6965512 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1655. Min Act: -0.1700
Data Index: 623295 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1343. Min Act: -0.1700
Data Index: 3932341 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1343. Min Act: -0.1700
Data Index: 6557946 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0718. Min Act: -0.1700
Data Index: 3618858 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.1343. Min Act: -0.1700
Data Index: 2526089 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0718. Min Act: -0.1700
Data Index: 4980279 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0405. Min Act: -0.1700
Data Index: 1792582 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0405. Min Act: -0.1700
Data Index: 2842436 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0093. Min Act: -0.1700
Data Index: 8650091 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0405. Min Act: -0.1700
Data Index: 4860526 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0405. Min Act: -0.1700
Data Index: 4580173 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0093. Min Act: -0.1700
Data Index: 2306571 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0093. Min Act: -0.1700
Data Index: 926087 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3843. Min Range: -5.3843
Max Act: 4.9780. Min Act: -0.1700
Data Index: 2963921 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3843. Min Range: -5.3843
Max Act: 5.0093. Min Act: -0.1700
Data Index: 3023767 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19