Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1761. Min Range: -3.1761
Max Act: 3.1761. Min Act: -0.1700
Data Index: 6786843 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.9394. Min Act: -0.1700
Data Index: 5083248 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8601. Min Act: -0.1700
Data Index: 6954927 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8760. Min Act: -0.1700
Data Index: 4207317 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.9236. Min Act: -0.1700
Data Index: 3397205 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8442. Min Act: -0.1700
Data Index: 1720018 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8601. Min Act: -0.1700
Data Index: 8307248 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8601. Min Act: -0.1700
Data Index: 4834542 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8760. Min Act: -0.1700
Data Index: 5846630 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8124. Min Act: -0.1700
Data Index: 3768267 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8124. Min Act: -0.1700
Data Index: 7371099 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.8124. Min Act: -0.1700
Data Index: 1727775 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7965. Min Act: -0.1700
Data Index: 3578966 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7965. Min Act: -0.1700
Data Index: 1681327 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7646. Min Act: -0.1700
Data Index: 6572782 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7327. Min Act: -0.1700
Data Index: 1434621 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7487. Min Act: -0.1700
Data Index: 7908174 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7327. Min Act: -0.1700
Data Index: 6944802 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7487. Min Act: -0.1700
Data Index: 1420837 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1761. Min Range: -3.1761
Max Act: 2.7806. Min Act: -0.1700
Data Index: 606072 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19