Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.8273. Min Act: -0.1700
Data Index: 6012228 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.8273. Min Act: -0.1700
Data Index: 773471 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7648. Min Act: -0.1700
Data Index: 288327 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7648. Min Act: -0.1700
Data Index: 5125502 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7648. Min Act: -0.1700
Data Index: 139042 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7648. Min Act: -0.1700
Data Index: 4952467 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7335. Min Act: -0.1700
Data Index: 8478973 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7335. Min Act: -0.1700
Data Index: 4799058 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7335. Min Act: -0.1700
Data Index: 7340861 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7022. Min Act: -0.1700
Data Index: 6794485 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7022. Min Act: -0.1700
Data Index: 1184227 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.7022. Min Act: -0.1700
Data Index: 5631956 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6709. Min Act: -0.1700
Data Index: 7700638 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6709. Min Act: -0.1700
Data Index: 5285800 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6709. Min Act: -0.1700
Data Index: 350744 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6709. Min Act: -0.1700
Data Index: 479056 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6709. Min Act: -0.1700
Data Index: 2828345 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6397. Min Act: -0.1700
Data Index: 4034111 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6397. Min Act: -0.1700
Data Index: 3672647 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8273. Min Range: -3.8273
Max Act: 3.6084. Min Act: -0.1700
Data Index: 3832032 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19