Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.4782. Min Act: -0.1700
Data Index: 400843 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.4311. Min Act: -0.1700
Data Index: 4913794 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.4155. Min Act: -0.1700
Data Index: 2242080 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3998. Min Act: -0.1700
Data Index: 2242081 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3684. Min Act: -0.1700
Data Index: 3466517 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3684. Min Act: -0.1700
Data Index: 3685560 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3527. Min Act: -0.1700
Data Index: 7787201 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3527. Min Act: -0.1700
Data Index: 7453470 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3371. Min Act: -0.1700
Data Index: 5065498 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3371. Min Act: -0.1700
Data Index: 5386955 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3371. Min Act: -0.1700
Data Index: 4464380 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3371. Min Act: -0.1700
Data Index: 7159442 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3371. Min Act: -0.1700
Data Index: 434842 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3214. Min Act: -0.1700
Data Index: 3005794 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3057. Min Act: -0.1700
Data Index: 5213191 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.3057. Min Act: -0.1700
Data Index: 7375360 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.2743. Min Act: -0.1700
Data Index: 553722 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.2900. Min Act: -0.1700
Data Index: 3600404 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.2900. Min Act: -0.1700
Data Index: 7000685 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4782. Min Range: -3.4782
Max Act: 3.2900. Min Act: -0.1700
Data Index: 740495 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19