Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3838 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.5958. Min Act: -0.1700
Data Index: 5995725 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.5646. Min Act: -0.1700
Data Index: 7358459 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.4708. Min Act: -0.1700
Data Index: 3888622 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2521. Min Act: -0.1700
Data Index: 1165267 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2521. Min Act: -0.1700
Data Index: 2817635 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2208. Min Act: -0.1700
Data Index: 8723653 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2208. Min Act: -0.1700
Data Index: 2013718 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2208. Min Act: -0.1700
Data Index: 3929194 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.1271. Min Act: -0.1700
Data Index: 8637171 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0958. Min Act: -0.1700
Data Index: 5701803 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 417563 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3360688 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 8411780 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 20696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3897118 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 7681130 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 4092853 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 1632775 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 4265216 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9708. Min Act: -0.1700
Data Index: 1921728 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19