Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4350 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4401262 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.1073. Min Act: -0.1700
Data Index: 8791309 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.1073. Min Act: -0.1700
Data Index: 3991589 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.0448. Min Act: -0.1700
Data Index: 1035891 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.0448. Min Act: -0.1700
Data Index: 7604488 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.9823. Min Act: -0.1700
Data Index: 453070 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 7863173 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7948. Min Act: -0.1700
Data Index: 2042218 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7948. Min Act: -0.1700
Data Index: 5177408 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7635. Min Act: -0.1700
Data Index: 5966166 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7323. Min Act: -0.1700
Data Index: 983761 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7635. Min Act: -0.1700
Data Index: 303220 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7323. Min Act: -0.1700
Data Index: 3892820 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7323. Min Act: -0.1700
Data Index: 5307720 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7010. Min Act: -0.1700
Data Index: 7114505 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7323. Min Act: -0.1700
Data Index: 865975 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7010. Min Act: -0.1700
Data Index: 8675565 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7010. Min Act: -0.1700
Data Index: 5899812 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7010. Min Act: -0.1700
Data Index: 3155196 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.7010. Min Act: -0.1700
Data Index: 4650279 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19