Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.8034. Min Act: -0.1700
Data Index: 1710994 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.6159. Min Act: -0.1700
Data Index: 1278955 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.4909. Min Act: -0.1700
Data Index: 8574829 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.4597. Min Act: -0.1700
Data Index: 3746087 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.4597. Min Act: -0.1700
Data Index: 6220309 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.3972. Min Act: -0.1700
Data Index: 4306413 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.3347. Min Act: -0.1700
Data Index: 2412489 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.3347. Min Act: -0.1700
Data Index: 8487806 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.3347. Min Act: -0.1700
Data Index: 7477846 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2722. Min Act: -0.1700
Data Index: 3072966 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2722. Min Act: -0.1700
Data Index: 2284022 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2722. Min Act: -0.1700
Data Index: 2505343 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 6714924 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2799383 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2824401 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2097. Min Act: -0.1700
Data Index: 1173870 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 1606897 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2097. Min Act: -0.1700
Data Index: 7095059 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 765490 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8034. Min Range: -6.8034
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2505342 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19