Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1237 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.2246. Min Act: -0.1700
Data Index: 4225574 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1933. Min Act: -0.1700
Data Index: 7498998 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1700
Data Index: 2413311 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9433. Min Act: -0.1700
Data Index: 7261495 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9433. Min Act: -0.1700
Data Index: 8343647 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9433. Min Act: -0.1700
Data Index: 5475143 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9121. Min Act: -0.1700
Data Index: 3149251 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9121. Min Act: -0.1700
Data Index: 7263004 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7294258 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9121. Min Act: -0.1700
Data Index: 1979182 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8808. Min Act: -0.1700
Data Index: 5110785 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7751731 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.9121. Min Act: -0.1700
Data Index: 1540562 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8496. Min Act: -0.1700
Data Index: 5523746 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8496. Min Act: -0.1700
Data Index: 5660328 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8496. Min Act: -0.1700
Data Index: 536111 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8496. Min Act: -0.1700
Data Index: 2721008 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8496. Min Act: -0.1700
Data Index: 4179124 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.8183. Min Act: -0.1700
Data Index: 6701271 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2246. Min Range: -5.2246
Max Act: 4.7871. Min Act: -0.1700
Data Index: 6352435 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19