Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.9745. Min Act: -0.1700
Data Index: 5563738 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.9120. Min Act: -0.1700
Data Index: 7079971 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.8808. Min Act: -0.1700
Data Index: 5984093 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.8808. Min Act: -0.1700
Data Index: 2686515 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.8808. Min Act: -0.1700
Data Index: 6854348 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.8495. Min Act: -0.1700
Data Index: 3873788 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.8183. Min Act: -0.1700
Data Index: 6857762 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7558. Min Act: -0.1700
Data Index: 7118991 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7870. Min Act: -0.1700
Data Index: 2649687 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7870. Min Act: -0.1700
Data Index: 3730010 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7558. Min Act: -0.1700
Data Index: 7166419 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7558. Min Act: -0.1700
Data Index: 5803605 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.6933. Min Act: -0.1700
Data Index: 4381701 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7245. Min Act: -0.1700
Data Index: 146025 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.6933. Min Act: -0.1700
Data Index: 3086970 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.7245. Min Act: -0.1700
Data Index: 1408232 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.6933. Min Act: -0.1700
Data Index: 7097049 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.6933. Min Act: -0.1700
Data Index: 5618566 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.6933. Min Act: -0.1700
Data Index: 104304 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9745. Min Range: -4.9745
Max Act: 4.6933. Min Act: -0.1700
Data Index: 5336749 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19