Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2340 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1820. Min Range: -5.1820
Max Act: 5.1820. Min Act: -0.1700
Data Index: 4427582 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1820. Min Range: -5.1820
Max Act: 5.1508. Min Act: -0.1700
Data Index: 7715044 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1820. Min Range: -5.1820
Max Act: 5.0570. Min Act: -0.1700
Data Index: 7662783 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9945. Min Act: -0.1700
Data Index: 6024015 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9945. Min Act: -0.1700
Data Index: 2920011 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9945. Min Act: -0.1700
Data Index: 7161372 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9633. Min Act: -0.1700
Data Index: 6995666 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9633. Min Act: -0.1700
Data Index: 4177790 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9320. Min Act: -0.1700
Data Index: 7356441 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9008. Min Act: -0.1700
Data Index: 839455 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9320. Min Act: -0.1700
Data Index: 6818187 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9320. Min Act: -0.1700
Data Index: 7966260 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9008. Min Act: -0.1700
Data Index: 2287899 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9008. Min Act: -0.1700
Data Index: 7619040 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9008. Min Act: -0.1700
Data Index: 892776 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.9008. Min Act: -0.1700
Data Index: 1754900 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.8383. Min Act: -0.1700
Data Index: 1780952 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.8695. Min Act: -0.1700
Data Index: 3217910 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.8695. Min Act: -0.1700
Data Index: 4731549 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1820. Min Range: -5.1820
Max Act: 4.8695. Min Act: -0.1700
Data Index: 985365 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19