Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2167 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.2836. Min Act: -0.1700
Data Index: 788466 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.2523. Min Act: -0.1700
Data Index: 8469140 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.1898. Min Act: -0.1700
Data Index: 878796 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.1898. Min Act: -0.1700
Data Index: 8013441 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.1898. Min Act: -0.1700
Data Index: 2897953 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.0961. Min Act: -0.1700
Data Index: 5816795 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.0961. Min Act: -0.1700
Data Index: 1389294 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.0648. Min Act: -0.1700
Data Index: 6605364 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2836. Min Range: -7.2836
Max Act: 7.0023. Min Act: -0.1700
Data Index: 5819158 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.9398. Min Act: -0.1700
Data Index: 5625701 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.9398. Min Act: -0.1700
Data Index: 6318177 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.9086. Min Act: -0.1700
Data Index: 7256363 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.8773. Min Act: -0.1700
Data Index: 248571 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.9086. Min Act: -0.1700
Data Index: 5073494 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.8773. Min Act: -0.1700
Data Index: 1172214 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.8773. Min Act: -0.1700
Data Index: 6076740 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.8148. Min Act: -0.1700
Data Index: 2217183 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.8148. Min Act: -0.1700
Data Index: 8393794 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.8148. Min Act: -0.1700
Data Index: 5445112 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2836. Min Range: -7.2836
Max Act: 6.7836. Min Act: -0.1700
Data Index: 378237 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19