Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2266 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.3135. Min Act: -0.1700
Data Index: 3014816 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.2197. Min Act: -0.1700
Data Index: 2989432 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.1885. Min Act: -0.1700
Data Index: 8655398 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.1572. Min Act: -0.1700
Data Index: 6842420 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.1260. Min Act: -0.1700
Data Index: 3694772 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.0635. Min Act: -0.1700
Data Index: 97089 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.0635. Min Act: -0.1700
Data Index: 498022 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.0635. Min Act: -0.1700
Data Index: 1204935 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3135. Min Range: -6.3135
Max Act: 6.0322. Min Act: -0.1700
Data Index: 4839370 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9697. Min Act: -0.1700
Data Index: 3558706 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7963332 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9385. Min Act: -0.1700
Data Index: 6807515 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9385. Min Act: -0.1700
Data Index: 8185355 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9072. Min Act: -0.1700
Data Index: 7352914 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9072. Min Act: -0.1700
Data Index: 7022282 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.9072. Min Act: -0.1700
Data Index: 2388057 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.8760. Min Act: -0.1700
Data Index: 1915783 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.8760. Min Act: -0.1700
Data Index: 2715781 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.8760. Min Act: -0.1700
Data Index: 2767473 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3135. Min Range: -6.3135
Max Act: 5.8447. Min Act: -0.1700
Data Index: 1182709 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19