Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3054. Min Act: -0.1700
Data Index: 3417257 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3679. Min Act: -0.1700
Data Index: 7697922 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3366. Min Act: -0.1700
Data Index: 2047192 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3366. Min Act: -0.1700
Data Index: 4923149 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3366. Min Act: -0.1700
Data Index: 1101128 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3054. Min Act: -0.1700
Data Index: 7399344 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2741. Min Act: -0.1700
Data Index: 572359 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2741. Min Act: -0.1700
Data Index: 2931362 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.3054. Min Act: -0.1700
Data Index: 1431130 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 5597322 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 1131027 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 1558096 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 4283494 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 5579897 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 6625646 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 3521091 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 4610179 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 223158 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2429. Min Act: -0.1700
Data Index: 7396935 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3679. Min Range: -4.3679
Max Act: 4.2116. Min Act: -0.1700
Data Index: 6768609 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19