Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.4283. Min Act: -0.1700
Data Index: 8548906 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.3971. Min Act: -0.1700
Data Index: 325792 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.3971. Min Act: -0.1700
Data Index: 6660586 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.3346. Min Act: -0.1700
Data Index: 7175851 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.3346. Min Act: -0.1700
Data Index: 2433403 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2721. Min Act: -0.1700
Data Index: 4053017 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2408. Min Act: -0.1700
Data Index: 7211028 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2408. Min Act: -0.1700
Data Index: 7359281 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2408. Min Act: -0.1700
Data Index: 7797842 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2408. Min Act: -0.1700
Data Index: 7963135 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2408. Min Act: -0.1700
Data Index: 470983 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2408. Min Act: -0.1700
Data Index: 8760581 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2096. Min Act: -0.1700
Data Index: 3376687 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.2096. Min Act: -0.1700
Data Index: 8492383 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.1783. Min Act: -0.1700
Data Index: 5225795 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.1470. Min Act: -0.1700
Data Index: 7727216 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.1783. Min Act: -0.1700
Data Index: 5711454 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.1783. Min Act: -0.1700
Data Index: 412754 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.1470. Min Act: -0.1700
Data Index: 2253577 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4283. Min Range: -4.4283
Max Act: 4.1470. Min Act: -0.1700
Data Index: 7016708 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19