Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2234. Min Range: -6.2234
Max Act: 6.2234. Min Act: -0.1700
Data Index: 5255587 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2234. Min Range: -6.2234
Max Act: 6.1922. Min Act: -0.1700
Data Index: 7412357 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2234. Min Range: -6.2234
Max Act: 6.1609. Min Act: -0.1700
Data Index: 2608098 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2234. Min Range: -6.2234
Max Act: 6.0359. Min Act: -0.1700
Data Index: 1175187 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9422. Min Act: -0.1700
Data Index: 1364906 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9109. Min Act: -0.1700
Data Index: 2557420 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9422. Min Act: -0.1700
Data Index: 7456690 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9109. Min Act: -0.1700
Data Index: 3690566 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9109. Min Act: -0.1700
Data Index: 3942235 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9109. Min Act: -0.1700
Data Index: 4150202 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.9109. Min Act: -0.1700
Data Index: 784276 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8484. Min Act: -0.1700
Data Index: 2906557 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8797. Min Act: -0.1700
Data Index: 5284805 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8797. Min Act: -0.1700
Data Index: 2441203 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7583603 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8484. Min Act: -0.1700
Data Index: 2999483 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8797. Min Act: -0.1700
Data Index: 7530271 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8172. Min Act: -0.1700
Data Index: 2372309 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8172. Min Act: -0.1700
Data Index: 1505451 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2234. Min Range: -6.2234
Max Act: 5.8172. Min Act: -0.1700
Data Index: 3220045 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19