Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.5731. Min Act: -0.1700
Data Index: 152267 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.5731. Min Act: -0.1700
Data Index: 4491187 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.5419. Min Act: -0.1700
Data Index: 5857253 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.4794. Min Act: -0.1700
Data Index: 6404837 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.4169. Min Act: -0.1700
Data Index: 5852970 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 4927666 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 2756594 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.4169. Min Act: -0.1700
Data Index: 2381252 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 8645749 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1921053 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 3509552 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1111878 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3543. Min Act: -0.1700
Data Index: 5062352 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.4169. Min Act: -0.1700
Data Index: 3137969 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1598315 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 4203169 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.4169. Min Act: -0.1700
Data Index: 3364757 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3856. Min Act: -0.1700
Data Index: 2794985 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3231. Min Act: -0.1700
Data Index: 2736186 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5731. Min Range: -4.5731
Max Act: 4.3543. Min Act: -0.1700
Data Index: 6020172 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19