Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5084 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0014. Min Range: -7.0014
Max Act: 7.0014. Min Act: -0.1700
Data Index: 6740679 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0014. Min Range: -7.0014
Max Act: 7.0014. Min Act: -0.1700
Data Index: 2513535 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.9389. Min Act: -0.1700
Data Index: 7194922 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.9076. Min Act: -0.1700
Data Index: 2964967 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.9389. Min Act: -0.1700
Data Index: 8224089 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.8764. Min Act: -0.1700
Data Index: 4817861 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.8139. Min Act: -0.1700
Data Index: 602644 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7514. Min Act: -0.1700
Data Index: 4320520 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.8139. Min Act: -0.1700
Data Index: 5364216 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7826. Min Act: -0.1700
Data Index: 439534 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7514. Min Act: -0.1700
Data Index: 4306685 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7514. Min Act: -0.1700
Data Index: 5536498 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7514. Min Act: -0.1700
Data Index: 8825723 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7514. Min Act: -0.1700
Data Index: 6415638 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.7514. Min Act: -0.1700
Data Index: 5057380 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.6889. Min Act: -0.1700
Data Index: 3735846 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.6889. Min Act: -0.1700
Data Index: 8051925 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.6889. Min Act: -0.1700
Data Index: 3087987 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.6889. Min Act: -0.1700
Data Index: 1980512 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0014. Min Range: -7.0014
Max Act: 6.6576. Min Act: -0.1700
Data Index: 2892997 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19