Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3288 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3827. Min Act: -0.1700
Data Index: 468001 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3827. Min Act: -0.1700
Data Index: 4581295 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3984. Min Act: -0.1700
Data Index: 7542121 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3670. Min Act: -0.1700
Data Index: 7800286 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3513. Min Act: -0.1700
Data Index: 8381747 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3513. Min Act: -0.1700
Data Index: 7672679 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3513. Min Act: -0.1700
Data Index: 8469602 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3513. Min Act: -0.1700
Data Index: 3157992 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3356. Min Act: -0.1700
Data Index: 5004187 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3356. Min Act: -0.1700
Data Index: 56551 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3356. Min Act: -0.1700
Data Index: 8077771 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3199. Min Act: -0.1700
Data Index: 6802733 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3356. Min Act: -0.1700
Data Index: 2423648 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3199. Min Act: -0.1700
Data Index: 8520833 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3356. Min Act: -0.1700
Data Index: 2338620 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3042. Min Act: -0.1700
Data Index: 6552400 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3199. Min Act: -0.1700
Data Index: 1844319 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3042. Min Act: -0.1700
Data Index: 7063326 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3199. Min Act: -0.1700
Data Index: 6254186 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3984. Min Range: -3.3984
Max Act: 3.3042. Min Act: -0.1700
Data Index: 3148950 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19