Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 90 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.9535. Min Act: -0.1700
Data Index: 7965475 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.8285. Min Act: -0.1700
Data Index: 956139 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.8285. Min Act: -0.1700
Data Index: 3974732 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.7035. Min Act: -0.1700
Data Index: 8792585 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.6410. Min Act: -0.1700
Data Index: 1131449 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.6410. Min Act: -0.1700
Data Index: 821890 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.5785. Min Act: -0.1700
Data Index: 3885985 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.5785. Min Act: -0.1700
Data Index: 2197719 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.5160. Min Act: -0.1700
Data Index: 5237869 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.5160. Min Act: -0.1700
Data Index: 4915843 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.4535. Min Act: -0.1700
Data Index: 6417586 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.4535. Min Act: -0.1700
Data Index: 4609799 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.4535. Min Act: -0.1700
Data Index: 1733046 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.3285. Min Act: -0.1700
Data Index: 5538263 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.3910. Min Act: -0.1700
Data Index: 5945027 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.3910. Min Act: -0.1700
Data Index: 3399308 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.3285. Min Act: -0.1700
Data Index: 2740440 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.3285. Min Act: -0.1700
Data Index: 6973485 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.2660. Min Act: -0.1700
Data Index: 474477 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9535. Min Range: -9.9535
Max Act: 9.2035. Min Act: -0.1700
Data Index: 1766057 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19