Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4282 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.2868. Min Act: -0.1700
Data Index: 380453 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.1926. Min Act: -0.1700
Data Index: 472050 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.1296. Min Act: -0.1700
Data Index: 2162097 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0981. Min Act: -0.1700
Data Index: 4142789 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0508. Min Act: -0.1700
Data Index: 4480270 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0666. Min Act: -0.1700
Data Index: 2674489 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0666. Min Act: -0.1700
Data Index: 8082065 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0350. Min Act: -0.1700
Data Index: 7623729 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0508. Min Act: -0.1700
Data Index: 8119537 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0350. Min Act: -0.1700
Data Index: 4244812 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0350. Min Act: -0.1700
Data Index: 6568562 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0508. Min Act: -0.1700
Data Index: 3309722 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0192. Min Act: -0.1700
Data Index: 7915641 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0350. Min Act: -0.1700
Data Index: 6938846 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0192. Min Act: -0.1700
Data Index: 4490401 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0350. Min Act: -0.1700
Data Index: 6979096 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0192. Min Act: -0.1700
Data Index: 2510236 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0034. Min Act: -0.1700
Data Index: 6092530 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0034. Min Act: -0.1700
Data Index: 4223007 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2868. Min Range: -3.2868
Max Act: 3.0034. Min Act: -0.1700
Data Index: 380462 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19