Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9555. Min Act: -0.1700
Data Index: 6112480 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9713. Min Act: -0.1700
Data Index: 4722971 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9713. Min Act: -0.1700
Data Index: 4722990 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9080. Min Act: -0.1700
Data Index: 8072918 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8921. Min Act: -0.1700
Data Index: 3488595 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9080. Min Act: -0.1700
Data Index: 8106732 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9238. Min Act: -0.1700
Data Index: 1606654 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8921. Min Act: -0.1700
Data Index: 8106730 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8762. Min Act: -0.1700
Data Index: 5469003 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.9080. Min Act: -0.1700
Data Index: 8653813 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8921. Min Act: -0.1700
Data Index: 5053667 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8921. Min Act: -0.1700
Data Index: 5053666 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8762. Min Act: -0.1700
Data Index: 8072901 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8604. Min Act: -0.1700
Data Index: 5434036 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8762. Min Act: -0.1700
Data Index: 4722976 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8445. Min Act: -0.1700
Data Index: 6757716 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8604. Min Act: -0.1700
Data Index: 4722987 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8921. Min Act: -0.1700
Data Index: 5806562 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8445. Min Act: -0.1700
Data Index: 6757705 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9713. Min Range: -2.9713
Max Act: 2.8604. Min Act: -0.1700
Data Index: 6360721 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19