Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1755. Min Act: -0.1700
Data Index: 8484148 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9880. Min Act: -0.1700
Data Index: 5788109 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9568. Min Act: -0.1700
Data Index: 6783456 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9255. Min Act: -0.1700
Data Index: 2111170 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 8429117 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 6254646 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8005. Min Act: -0.1700
Data Index: 4300109 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 1383583 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 6735523 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3583168 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5114462 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6443. Min Act: -0.1700
Data Index: 1336406 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6443. Min Act: -0.1700
Data Index: 4385491 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.5818. Min Act: -0.1700
Data Index: 5043365 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6130. Min Act: -0.1700
Data Index: 6985051 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6130. Min Act: -0.1700
Data Index: 2789774 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.5818. Min Act: -0.1700
Data Index: 3388784 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.5505. Min Act: -0.1700
Data Index: 8273031 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.5505. Min Act: -0.1700
Data Index: 8501756 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.4880. Min Act: -0.1700
Data Index: 3945296 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19