Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.7675. Min Act: -0.1700
Data Index: 7519211 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.7050. Min Act: -0.1700
Data Index: 1806534 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.6737. Min Act: -0.1700
Data Index: 2530581 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.6111. Min Act: -0.1700
Data Index: 1854632 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5798. Min Act: -0.1700
Data Index: 3281147 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 6861442 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 1211454 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 1726462 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 995168 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 5857330 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 5866045 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 7079189 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 4551941 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 7163815 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 110981 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 6754841 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 1303734 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 373218 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5172. Min Act: -0.1700
Data Index: 6386002 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5485. Min Act: -0.1700
Data Index: 2081378 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19