Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0518. Min Range: -6.0518
Max Act: 6.0518. Min Act: -0.1700
Data Index: 366219 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0518. Min Range: -6.0518
Max Act: 6.0206. Min Act: -0.1700
Data Index: 1212203 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0518. Min Range: -6.0518
Max Act: 6.0206. Min Act: -0.1700
Data Index: 3070435 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.8331. Min Act: -0.1700
Data Index: 1971396 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.8018. Min Act: -0.1700
Data Index: 5227209 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.7706. Min Act: -0.1700
Data Index: 3229042 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.7393. Min Act: -0.1700
Data Index: 224036 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.7081. Min Act: -0.1700
Data Index: 4790735 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.7081. Min Act: -0.1700
Data Index: 5822214 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.6456. Min Act: -0.1700
Data Index: 3151151 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.6456. Min Act: -0.1700
Data Index: 4615210 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.6456. Min Act: -0.1700
Data Index: 6185758 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.6456. Min Act: -0.1700
Data Index: 7387771 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.6456. Min Act: -0.1700
Data Index: 6277265 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.5831. Min Act: -0.1700
Data Index: 7711560 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.5831. Min Act: -0.1700
Data Index: 2397494 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.5831. Min Act: -0.1700
Data Index: 1480501 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.5518. Min Act: -0.1700
Data Index: 5830042 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.5518. Min Act: -0.1700
Data Index: 8499352 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0518. Min Range: -6.0518
Max Act: 5.5206. Min Act: -0.1700
Data Index: 1370624 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19