Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6105 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.3214. Min Act: -0.1700
Data Index: 1812610 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.2276. Min Act: -0.1700
Data Index: 2542324 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.2276. Min Act: -0.1700
Data Index: 1038226 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.1339. Min Act: -0.1700
Data Index: 4260108 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.1026. Min Act: -0.1700
Data Index: 5752309 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0714. Min Act: -0.1700
Data Index: 8650578 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0714. Min Act: -0.1700
Data Index: 5117329 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0714. Min Act: -0.1700
Data Index: 2005863 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0714. Min Act: -0.1700
Data Index: 7397955 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0401. Min Act: -0.1700
Data Index: 4186009 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0401. Min Act: -0.1700
Data Index: 374546 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0088. Min Act: -0.1700
Data Index: 2957488 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0088. Min Act: -0.1700
Data Index: 7582608 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0088. Min Act: -0.1700
Data Index: 4565281 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0088. Min Act: -0.1700
Data Index: 7295925 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3214. Min Range: -4.3214
Max Act: 4.0088. Min Act: -0.1700
Data Index: 6528441 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3214. Min Range: -4.3214
Max Act: 3.9776. Min Act: -0.1700
Data Index: 1973686 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3214. Min Range: -4.3214
Max Act: 3.9776. Min Act: -0.1700
Data Index: 2157827 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3214. Min Range: -4.3214
Max Act: 3.9463. Min Act: -0.1700
Data Index: 4968073 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3214. Min Range: -4.3214
Max Act: 3.9463. Min Act: -0.1700
Data Index: 1020376 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19