Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 767 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.9963. Min Act: -0.1700
Data Index: 1660534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.8713. Min Act: -0.1700
Data Index: 3054234 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.8087. Min Act: -0.1700
Data Index: 3442750 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.8087. Min Act: -0.1700
Data Index: 1637937 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.8087. Min Act: -0.1700
Data Index: 2859192 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.8087. Min Act: -0.1700
Data Index: 2339749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 38481 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 2382283 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 5525331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 2117550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 3442748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7149. Min Act: -0.1700
Data Index: 4792852 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 7184781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.8087. Min Act: -0.1700
Data Index: 6113559 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7774. Min Act: -0.1700
Data Index: 6058773 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7462. Min Act: -0.1700
Data Index: 7492484 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7149. Min Act: -0.1700
Data Index: 3765648 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7149. Min Act: -0.1700
Data Index: 1437101 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.7149. Min Act: -0.1700
Data Index: 2364821 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9963. Min Range: -3.9963
Max Act: 3.6836. Min Act: -0.1700
Data Index: 1947343 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19