Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0609. Min Range: -7.0609
Max Act: 7.0609. Min Act: -0.1700
Data Index: 6952185 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.8421. Min Act: -0.1700
Data Index: 6197939 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.7796. Min Act: -0.1700
Data Index: 3816570 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.7796. Min Act: -0.1700
Data Index: 263192 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.7796. Min Act: -0.1700
Data Index: 1015219 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.6234. Min Act: -0.1700
Data Index: 6698234 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.5609. Min Act: -0.1700
Data Index: 5951717 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.5609. Min Act: -0.1700
Data Index: 4055568 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.5296. Min Act: -0.1700
Data Index: 1701432 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.5296. Min Act: -0.1700
Data Index: 6262196 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4984. Min Act: -0.1700
Data Index: 7925458 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4671. Min Act: -0.1700
Data Index: 1048975 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4671. Min Act: -0.1700
Data Index: 6281492 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4671. Min Act: -0.1700
Data Index: 4094723 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4359. Min Act: -0.1700
Data Index: 2856646 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4046. Min Act: -0.1700
Data Index: 4760948 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4359. Min Act: -0.1700
Data Index: 444915 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4046. Min Act: -0.1700
Data Index: 3323112 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4046. Min Act: -0.1700
Data Index: 3095861 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0609. Min Range: -7.0609
Max Act: 6.4046. Min Act: -0.1700
Data Index: 6766292 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19