Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3097. Min Range: -6.3097
Max Act: 6.3097. Min Act: -0.1700
Data Index: 1738590 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3097. Min Range: -6.3097
Max Act: 6.0284. Min Act: -0.1700
Data Index: 5686508 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.9659. Min Act: -0.1700
Data Index: 326041 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.9347. Min Act: -0.1700
Data Index: 6160571 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.8722. Min Act: -0.1700
Data Index: 947766 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.8722. Min Act: -0.1700
Data Index: 2576718 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.8409. Min Act: -0.1700
Data Index: 7278197 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.8409. Min Act: -0.1700
Data Index: 544003 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.8097. Min Act: -0.1700
Data Index: 7012437 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.8097. Min Act: -0.1700
Data Index: 4148081 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7784. Min Act: -0.1700
Data Index: 1371753 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7784. Min Act: -0.1700
Data Index: 4935695 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7472. Min Act: -0.1700
Data Index: 8715291 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7472. Min Act: -0.1700
Data Index: 6384836 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7472. Min Act: -0.1700
Data Index: 6832983 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7159. Min Act: -0.1700
Data Index: 5320145 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7159. Min Act: -0.1700
Data Index: 1780680 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.7159. Min Act: -0.1700
Data Index: 7557175 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.6847. Min Act: -0.1700
Data Index: 5113879 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3097. Min Range: -6.3097
Max Act: 5.6534. Min Act: -0.1700
Data Index: 5063641 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19