Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2625. Min Range: -3.2625
Max Act: 3.2625. Min Act: -0.1700
Data Index: 2426532 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2625. Min Range: -3.2625
Max Act: 3.0579. Min Act: -0.1700
Data Index: 6868160 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2625. Min Range: -3.2625
Max Act: 3.0263. Min Act: -0.1700
Data Index: 704888 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2625. Min Range: -3.2625
Max Act: 3.0421. Min Act: -0.1700
Data Index: 1857743 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9789. Min Act: -0.1700
Data Index: 4900549 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9947. Min Act: -0.1700
Data Index: 5480849 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9947. Min Act: -0.1700
Data Index: 6086882 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9947. Min Act: -0.1700
Data Index: 3855122 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9631. Min Act: -0.1700
Data Index: 241924 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9631. Min Act: -0.1700
Data Index: 5721620 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9789. Min Act: -0.1700
Data Index: 4818712 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9631. Min Act: -0.1700
Data Index: 4096209 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9472. Min Act: -0.1700
Data Index: 5431143 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9472. Min Act: -0.1700
Data Index: 2787680 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9472. Min Act: -0.1700
Data Index: 6635523 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9472. Min Act: -0.1700
Data Index: 3495688 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9472. Min Act: -0.1700
Data Index: 1910388 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9156. Min Act: -0.1700
Data Index: 8767532 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9156. Min Act: -0.1700
Data Index: 4488311 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2625. Min Range: -3.2625
Max Act: 2.9156. Min Act: -0.1700
Data Index: 4351532 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19