Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.5722. Min Act: -0.1700
Data Index: 8157197 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.5097. Min Act: -0.1700
Data Index: 8076842 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.4472. Min Act: -0.1700
Data Index: 5155208 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.3534. Min Act: -0.1700
Data Index: 4753791 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.3534. Min Act: -0.1700
Data Index: 2032298 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.2597. Min Act: -0.1700
Data Index: 6694310 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.2284. Min Act: -0.1700
Data Index: 2255645 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.2284. Min Act: -0.1700
Data Index: 7238804 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1659. Min Act: -0.1700
Data Index: 8365767 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1972. Min Act: -0.1700
Data Index: 4137306 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1972. Min Act: -0.1700
Data Index: 7279033 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1347. Min Act: -0.1700
Data Index: 1539628 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1659. Min Act: -0.1700
Data Index: 7506741 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1659. Min Act: -0.1700
Data Index: 8279135 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1659. Min Act: -0.1700
Data Index: 469847 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1347. Min Act: -0.1700
Data Index: 1397032 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1659. Min Act: -0.1700
Data Index: 1802325 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1347. Min Act: -0.1700
Data Index: 4197634 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.0722. Min Act: -0.1700
Data Index: 1649253 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5722. Min Range: -7.5722
Max Act: 7.1034. Min Act: -0.1700
Data Index: 6811571 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19