Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 971 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.7796. Min Act: -0.1700
Data Index: 3550304 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.7710. Min Act: -0.1700
Data Index: 6652591 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.7364. Min Act: -0.1700
Data Index: 1332089 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.7018. Min Act: -0.1699
Data Index: 8540583 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6931. Min Act: -0.1700
Data Index: 3727929 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6671. Min Act: -0.1700
Data Index: 6596734 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6758. Min Act: -0.1700
Data Index: 644365 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6671. Min Act: -0.1700
Data Index: 825817 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6671. Min Act: -0.1700
Data Index: 3163874 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6671. Min Act: -0.1699
Data Index: 2801572 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6671. Min Act: -0.1700
Data Index: 6697770 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6671. Min Act: -0.1700
Data Index: 3730953 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6584. Min Act: -0.1700
Data Index: 3452802 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6497. Min Act: -0.1700
Data Index: 6854633 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6410. Min Act: -0.1700
Data Index: 1766217 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6410. Min Act: -0.1700
Data Index: 3124735 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6410. Min Act: -0.1700
Data Index: 5204348 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6235. Min Act: -0.1699
Data Index: 4843665 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6410. Min Act: -0.1700
Data Index: 35984 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7796. Min Range: -1.7796
Max Act: 1.6323. Min Act: -0.1700
Data Index: 47388 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19