Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.4204. Min Act: -0.1700
Data Index: 4154205 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.2954. Min Act: -0.1700
Data Index: 1440782 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.2329. Min Act: -0.1700
Data Index: 3707945 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.2329. Min Act: -0.1700
Data Index: 755295 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.2329. Min Act: -0.1700
Data Index: 7858977 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.2017. Min Act: -0.1700
Data Index: 5072249 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.2017. Min Act: -0.1700
Data Index: 3747101 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.1704. Min Act: -0.1700
Data Index: 1072617 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.1704. Min Act: -0.1700
Data Index: 3622923 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.1079. Min Act: -0.1700
Data Index: 3753938 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.1079. Min Act: -0.1700
Data Index: 1953166 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0767. Min Act: -0.1700
Data Index: 4992470 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0767. Min Act: -0.1700
Data Index: 1407347 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0454. Min Act: -0.1700
Data Index: 1959166 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0142. Min Act: -0.1700
Data Index: 4752239 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0142. Min Act: -0.1700
Data Index: 5682220 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0142. Min Act: -0.1700
Data Index: 816069 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0142. Min Act: -0.1700
Data Index: 6294539 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0142. Min Act: -0.1700
Data Index: 3705610 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4204. Min Range: -6.4204
Max Act: 6.0142. Min Act: -0.1700
Data Index: 3931120 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19