Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3751 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.7483. Min Act: -0.1700
Data Index: 793503 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.4045. Min Act: -0.1700
Data Index: 8735906 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0920. Min Act: -0.1700
Data Index: 7000940 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.1233. Min Act: -0.1700
Data Index: 1230849 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0920. Min Act: -0.1700
Data Index: 8669827 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0920. Min Act: -0.1700
Data Index: 5566565 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0608. Min Act: -0.1700
Data Index: 1230848 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0608. Min Act: -0.1700
Data Index: 4376962 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0608. Min Act: -0.1700
Data Index: 8699379 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0295. Min Act: -0.1700
Data Index: 4507552 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7483. Min Range: -6.7483
Max Act: 6.0608. Min Act: -0.1700
Data Index: 3307416 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9670. Min Act: -0.1700
Data Index: 6305477 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9983. Min Act: -0.1700
Data Index: 2821666 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9670. Min Act: -0.1700
Data Index: 3002298 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9045. Min Act: -0.1700
Data Index: 2582284 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9045. Min Act: -0.1700
Data Index: 2074946 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.8733. Min Act: -0.1700
Data Index: 5866851 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.8733. Min Act: -0.1700
Data Index: 306635 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9045. Min Act: -0.1700
Data Index: 2582283 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7483. Min Range: -6.7483
Max Act: 5.9358. Min Act: -0.1700
Data Index: 6755777 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19