Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5651. Min Range: -5.5651
Max Act: 5.5651. Min Act: -0.1700
Data Index: 7540209 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.9714. Min Act: -0.1700
Data Index: 5907357 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.9714. Min Act: -0.1700
Data Index: 4676754 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.8151. Min Act: -0.1700
Data Index: 2030183 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.8151. Min Act: -0.1700
Data Index: 306754 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.7214. Min Act: -0.1700
Data Index: 2812414 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.6589. Min Act: -0.1700
Data Index: 5201650 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5964. Min Act: -0.1700
Data Index: 4679477 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5651. Min Act: -0.1700
Data Index: 3084441 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5651. Min Act: -0.1700
Data Index: 6288134 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5964. Min Act: -0.1700
Data Index: 1354344 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5651. Min Act: -0.1700
Data Index: 2821705 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5026. Min Act: -0.1700
Data Index: 8683965 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.5026. Min Act: -0.1700
Data Index: 8196356 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.4714. Min Act: -0.1700
Data Index: 108950 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.4714. Min Act: -0.1700
Data Index: 3640052 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.4401. Min Act: -0.1700
Data Index: 3831761 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.4714. Min Act: -0.1700
Data Index: 6071575 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.4714. Min Act: -0.1700
Data Index: 289668 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5651. Min Range: -5.5651
Max Act: 4.4401. Min Act: -0.1700
Data Index: 6415083 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19