Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 234 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.2593. Min Act: -0.1700
Data Index: 8137063 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.1030. Min Act: -0.1700
Data Index: 8137062 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.1030. Min Act: -0.1700
Data Index: 2284945 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.0718. Min Act: -0.1700
Data Index: 3724944 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.0405. Min Act: -0.1700
Data Index: 6089078 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.1030. Min Act: -0.1700
Data Index: 398837 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.0249. Min Act: -0.1700
Data Index: 4601718 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.0092. Min Act: -0.1700
Data Index: 117481 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.0249. Min Act: -0.1700
Data Index: 8137060 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2593. Min Range: -4.2593
Max Act: 4.0405. Min Act: -0.1700
Data Index: 4744186 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.9623. Min Act: -0.1700
Data Index: 6668666 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.9311. Min Act: -0.1700
Data Index: 7032730 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.9154. Min Act: -0.1700
Data Index: 3724933 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.8529. Min Act: -0.1700
Data Index: 8522688 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.9467. Min Act: -0.1700
Data Index: 4860380 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.8842. Min Act: -0.1700
Data Index: 6888743 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.8842. Min Act: -0.1700
Data Index: 1689189 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.8998. Min Act: -0.1700
Data Index: 4860377 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.9311. Min Act: -0.1700
Data Index: 2829438 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2593. Min Range: -4.2593
Max Act: 3.9311. Min Act: -0.1700
Data Index: 135803 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19