Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.2976. Min Act: -0.1700
Data Index: 7368584 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.1413. Min Act: -0.1700
Data Index: 4690217 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.0788. Min Act: -0.1700
Data Index: 4006641 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.1101. Min Act: -0.1700
Data Index: 7321874 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.1101. Min Act: -0.1700
Data Index: 7944440 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.0163. Min Act: -0.1700
Data Index: 547229 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2976. Min Range: -6.2976
Max Act: 6.0163. Min Act: -0.1700
Data Index: 4393718 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.9851. Min Act: -0.1700
Data Index: 3876526 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3308959 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3855863 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.9538. Min Act: -0.1700
Data Index: 6046813 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8601. Min Act: -0.1700
Data Index: 7876103 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8913. Min Act: -0.1700
Data Index: 1234855 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8913. Min Act: -0.1700
Data Index: 5536632 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8601. Min Act: -0.1700
Data Index: 1517070 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8601. Min Act: -0.1700
Data Index: 3576233 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8601. Min Act: -0.1700
Data Index: 4089170 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8288. Min Act: -0.1700
Data Index: 5627791 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8913. Min Act: -0.1700
Data Index: 5432954 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2976. Min Range: -6.2976
Max Act: 5.8288. Min Act: -0.1700
Data Index: 7055332 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19