Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.8217. Min Act: -0.1700
Data Index: 4400478 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.7592. Min Act: -0.1700
Data Index: 5687057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.7592. Min Act: -0.1700
Data Index: 7067083 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.7592. Min Act: -0.1700
Data Index: 3084981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.7592. Min Act: -0.1700
Data Index: 3035859 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.8217. Min Act: -0.1700
Data Index: 4188993 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.7592. Min Act: -0.1700
Data Index: 5041144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6967. Min Act: -0.1700
Data Index: 2346441 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6967. Min Act: -0.1700
Data Index: 1689943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6967. Min Act: -0.1700
Data Index: 5823628 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6967. Min Act: -0.1700
Data Index: 6800394 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 5092650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 4238504 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 5709624 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 5712567 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 94171 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 737158 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 2131992 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 3831050 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8217. Min Range: -7.8217
Max Act: 7.6342. Min Act: -0.1700
Data Index: 4229200 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19