Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2108 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5478. Min Range: -6.5478
Max Act: 6.5478. Min Act: -0.1700
Data Index: 6033671 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5478. Min Range: -6.5478
Max Act: 6.2353. Min Act: -0.1700
Data Index: 3938512 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5478. Min Range: -6.5478
Max Act: 6.2353. Min Act: -0.1700
Data Index: 5483211 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.9541. Min Act: -0.1700
Data Index: 6648162 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.8916. Min Act: -0.1700
Data Index: 8556100 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.8291. Min Act: -0.1700
Data Index: 7204938 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.7978. Min Act: -0.1700
Data Index: 2925870 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.8291. Min Act: -0.1700
Data Index: 1895383 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.7353. Min Act: -0.1700
Data Index: 4608238 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.7041. Min Act: -0.1700
Data Index: 1549579 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6728. Min Act: -0.1700
Data Index: 7951052 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6728. Min Act: -0.1700
Data Index: 6162145 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6728. Min Act: -0.1700
Data Index: 5722456 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6416. Min Act: -0.1700
Data Index: 3025625 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 5633485 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 2018725 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 913768 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 3105322 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6416. Min Act: -0.1700
Data Index: 8821514 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5478. Min Range: -6.5478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 7763226 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19