Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5739 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.4811. Min Act: -0.1700
Data Index: 6015334 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.2624. Min Act: -0.1700
Data Index: 2577712 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.2624. Min Act: -0.1700
Data Index: 7323315 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.2311. Min Act: -0.1700
Data Index: 8828721 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.2311. Min Act: -0.1700
Data Index: 4549204 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1999. Min Act: -0.1700
Data Index: 5999556 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1999. Min Act: -0.1700
Data Index: 3091507 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1999. Min Act: -0.1700
Data Index: 4510245 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1999. Min Act: -0.1700
Data Index: 2279325 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1686. Min Act: -0.1700
Data Index: 1681845 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1686. Min Act: -0.1700
Data Index: 8436138 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1999. Min Act: -0.1700
Data Index: 8197075 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1686. Min Act: -0.1700
Data Index: 4834604 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1686. Min Act: -0.1700
Data Index: 3748197 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1686. Min Act: -0.1700
Data Index: 4223043 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1374. Min Act: -0.1700
Data Index: 976959 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1374. Min Act: -0.1700
Data Index: 4877218 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1061. Min Act: -0.1700
Data Index: 7683676 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1374. Min Act: -0.1700
Data Index: 332374 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4811. Min Range: -6.4811
Max Act: 6.1374. Min Act: -0.1700
Data Index: 2588319 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19