Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.2994. Min Act: -0.1700
Data Index: 2263864 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.2056. Min Act: -0.1700
Data Index: 6324559 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0806. Min Act: -0.1700
Data Index: 2272004 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.1119. Min Act: -0.1700
Data Index: 4099462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.1119. Min Act: -0.1700
Data Index: 2504299 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0806. Min Act: -0.1700
Data Index: 602827 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0806. Min Act: -0.1700
Data Index: 2011435 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0806. Min Act: -0.1700
Data Index: 3970081 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0806. Min Act: -0.1700
Data Index: 203397 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0181. Min Act: -0.1700
Data Index: 2977648 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0806. Min Act: -0.1700
Data Index: 2011614 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0494. Min Act: -0.1700
Data Index: 162803 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0494. Min Act: -0.1700
Data Index: 6912083 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9868. Min Act: -0.1700
Data Index: 6006638 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9868. Min Act: -0.1700
Data Index: 4079998 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9868. Min Act: -0.1700
Data Index: 3150349 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9868. Min Act: -0.1700
Data Index: 25061 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0181. Min Act: -0.1700
Data Index: 3254037 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0181. Min Act: -0.1700
Data Index: 928135 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.0181. Min Act: -0.1700
Data Index: 5220753 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19