Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.6900. Min Act: -0.1700
Data Index: 5036061 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.6588. Min Act: -0.1700
Data Index: 4477067 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.5650. Min Act: -0.1700
Data Index: 7939344 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.5650. Min Act: -0.1700
Data Index: 971908 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.5025. Min Act: -0.1700
Data Index: 3240617 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.4713. Min Act: -0.1700
Data Index: 7548745 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.4400. Min Act: -0.1700
Data Index: 7876973 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.3463. Min Act: -0.1700
Data Index: 1478385 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.3150. Min Act: -0.1700
Data Index: 5913967 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.2525. Min Act: -0.1700
Data Index: 5814275 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.2213. Min Act: -0.1700
Data Index: 2025866 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.2213. Min Act: -0.1700
Data Index: 3513366 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1900. Min Act: -0.1700
Data Index: 4846566 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1900. Min Act: -0.1700
Data Index: 4558906 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1588. Min Act: -0.1700
Data Index: 2973618 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1588. Min Act: -0.1700
Data Index: 8098187 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1588. Min Act: -0.1700
Data Index: 1153129 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1588. Min Act: -0.1700
Data Index: 2763518 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1588. Min Act: -0.1700
Data Index: 318763 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6900. Min Range: -6.6900
Max Act: 6.1275. Min Act: -0.1700
Data Index: 3270076 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19