Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2570. Min Range: -7.2570
Max Act: 7.2570. Min Act: -0.1700
Data Index: 3667333 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2570. Min Range: -7.2570
Max Act: 7.0383. Min Act: -0.1700
Data Index: 4544475 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.9758. Min Act: -0.1700
Data Index: 3085530 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.9758. Min Act: -0.1700
Data Index: 1772275 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.9445. Min Act: -0.1700
Data Index: 6239492 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.8820. Min Act: -0.1700
Data Index: 1223885 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.8820. Min Act: -0.1700
Data Index: 3872201 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.8820. Min Act: -0.1700
Data Index: 7434391 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.8195. Min Act: -0.1700
Data Index: 135341 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.8195. Min Act: -0.1700
Data Index: 827700 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6945. Min Act: -0.1700
Data Index: 1110822 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6633. Min Act: -0.1700
Data Index: 5392472 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6633. Min Act: -0.1700
Data Index: 2672832 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6633. Min Act: -0.1700
Data Index: 6111133 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6008. Min Act: -0.1700
Data Index: 2783985 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6320. Min Act: -0.1700
Data Index: 5327434 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6633. Min Act: -0.1700
Data Index: 6552273 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6008. Min Act: -0.1700
Data Index: 5217847 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.6320. Min Act: -0.1700
Data Index: 7572906 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2570. Min Range: -7.2570
Max Act: 6.5695. Min Act: -0.1700
Data Index: 6247975 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19