Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2933. Min Range: -6.2933
Max Act: 6.2933. Min Act: -0.1700
Data Index: 8222450 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2933. Min Range: -6.2933
Max Act: 6.1683. Min Act: -0.1700
Data Index: 2619493 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2933. Min Range: -6.2933
Max Act: 6.0121. Min Act: -0.1700
Data Index: 2344361 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.9808. Min Act: -0.1700
Data Index: 530159 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.9808. Min Act: -0.1700
Data Index: 7487253 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.9496. Min Act: -0.1700
Data Index: 4262351 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.9183. Min Act: -0.1700
Data Index: 7149400 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.8246. Min Act: -0.1700
Data Index: 2451039 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.8871. Min Act: -0.1700
Data Index: 5480234 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.8558. Min Act: -0.1700
Data Index: 2673783 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.7933. Min Act: -0.1700
Data Index: 2512309 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.8246. Min Act: -0.1700
Data Index: 1079718 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.7621. Min Act: -0.1700
Data Index: 3031032 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.7621. Min Act: -0.1700
Data Index: 2067395 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.7308. Min Act: -0.1700
Data Index: 7734325 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.7308. Min Act: -0.1700
Data Index: 390587 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.7621. Min Act: -0.1700
Data Index: 1479245 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.6996. Min Act: -0.1700
Data Index: 1334579 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.6683. Min Act: -0.1700
Data Index: 3427965 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2933. Min Range: -6.2933
Max Act: 5.6683. Min Act: -0.1700
Data Index: 5174232 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19