Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1396 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.3983. Min Act: -0.1700
Data Index: 1404479 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.3358. Min Act: -0.1700
Data Index: 5940076 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.2733. Min Act: -0.1700
Data Index: 2678086 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.2733. Min Act: -0.1700
Data Index: 7627647 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.2108. Min Act: -0.1700
Data Index: 5493981 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1483. Min Act: -0.1700
Data Index: 4197149 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1483. Min Act: -0.1700
Data Index: 3970200 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1483. Min Act: -0.1700
Data Index: 3779413 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1170. Min Act: -0.1700
Data Index: 1410573 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1170. Min Act: -0.1700
Data Index: 7988616 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1170. Min Act: -0.1700
Data Index: 911690 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.1170. Min Act: -0.1700
Data Index: 3491439 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0858. Min Act: -0.1700
Data Index: 2219502 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0858. Min Act: -0.1700
Data Index: 3037910 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0858. Min Act: -0.1700
Data Index: 2798646 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0233. Min Act: -0.1700
Data Index: 1433902 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0545. Min Act: -0.1700
Data Index: 2453100 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0545. Min Act: -0.1700
Data Index: 6795026 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0545. Min Act: -0.1700
Data Index: 99496 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3983. Min Range: -7.3983
Max Act: 7.0233. Min Act: -0.1700
Data Index: 612744 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19