Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0155. Min Range: -6.0155
Max Act: 6.0155. Min Act: -0.1700
Data Index: 1242460 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7967. Min Act: -0.1700
Data Index: 4374330 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7967. Min Act: -0.1700
Data Index: 7534007 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7967. Min Act: -0.1700
Data Index: 1932229 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7655. Min Act: -0.1700
Data Index: 8163277 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.7342. Min Act: -0.1700
Data Index: 3932062 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.6405. Min Act: -0.1700
Data Index: 8610736 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.6405. Min Act: -0.1700
Data Index: 8129299 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.6092. Min Act: -0.1700
Data Index: 2329641 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5780. Min Act: -0.1700
Data Index: 7243557 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5780. Min Act: -0.1700
Data Index: 4329682 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5467. Min Act: -0.1700
Data Index: 1686327 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5467. Min Act: -0.1700
Data Index: 5382697 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5467. Min Act: -0.1700
Data Index: 7314833 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.4842. Min Act: -0.1700
Data Index: 4387545 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.4842. Min Act: -0.1700
Data Index: 2122052 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5155. Min Act: -0.1700
Data Index: 1057424 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.4842. Min Act: -0.1700
Data Index: 6059916 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.4842. Min Act: -0.1700
Data Index: 5562705 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0155. Min Range: -6.0155
Max Act: 5.5155. Min Act: -0.1700
Data Index: 8144376 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19