Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.8487. Min Act: -0.1700
Data Index: 6827688 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.6299. Min Act: -0.1700
Data Index: 1628022 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.5987. Min Act: -0.1700
Data Index: 5709127 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.6299. Min Act: -0.1700
Data Index: 3960770 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.5362. Min Act: -0.1700
Data Index: 5862466 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.5362. Min Act: -0.1700
Data Index: 698270 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.5362. Min Act: -0.1700
Data Index: 6630809 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4737. Min Act: -0.1700
Data Index: 5505633 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.5049. Min Act: -0.1700
Data Index: 498019 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4737. Min Act: -0.1700
Data Index: 8094092 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4737. Min Act: -0.1700
Data Index: 4215681 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4737. Min Act: -0.1700
Data Index: 5556542 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4424. Min Act: -0.1700
Data Index: 1001471 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4112. Min Act: -0.1700
Data Index: 5320668 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4112. Min Act: -0.1700
Data Index: 1691494 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.4112. Min Act: -0.1700
Data Index: 6529681 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.3799. Min Act: -0.1700
Data Index: 6310636 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.3799. Min Act: -0.1700
Data Index: 2051160 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.3799. Min Act: -0.1700
Data Index: 951293 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8487. Min Range: -5.8487
Max Act: 5.3799. Min Act: -0.1700
Data Index: 702608 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19