Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.9655. Min Act: -0.1700
Data Index: 6429049 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.9030. Min Act: -0.1700
Data Index: 7514685 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.7780. Min Act: -0.1700
Data Index: 792287 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.6530. Min Act: -0.1700
Data Index: 4714460 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.5280. Min Act: -0.1700
Data Index: 4971705 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.4655. Min Act: -0.1700
Data Index: 2546457 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.4655. Min Act: -0.1700
Data Index: 2787335 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.4655. Min Act: -0.1700
Data Index: 7304880 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.4030. Min Act: -0.1700
Data Index: 1378763 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.3405. Min Act: -0.1700
Data Index: 2849304 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.3405. Min Act: -0.1700
Data Index: 1374092 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.2780. Min Act: -0.1700
Data Index: 4853389 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.2780. Min Act: -0.1700
Data Index: 1365061 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.2155. Min Act: -0.1700
Data Index: 2951313 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.2155. Min Act: -0.1700
Data Index: 76824 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.2780. Min Act: -0.1700
Data Index: 2787384 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.1530. Min Act: -0.1700
Data Index: 8164720 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.1530. Min Act: -0.1700
Data Index: 4386503 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.0905. Min Act: -0.1700
Data Index: 7234639 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9655. Min Range: -8.9655
Max Act: 8.0905. Min Act: -0.1700
Data Index: 3925390 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19