Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.4410. Min Act: -0.1700
Data Index: 7465687 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.3469. Min Act: -0.1700
Data Index: 365863 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.2841. Min Act: -0.1700
Data Index: 2917212 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.2527. Min Act: -0.1700
Data Index: 2812910 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.2527. Min Act: -0.1700
Data Index: 5228819 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.2213. Min Act: -0.1700
Data Index: 3817189 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.2213. Min Act: -0.1700
Data Index: 3150015 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.2055. Min Act: -0.1700
Data Index: 4441270 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1741. Min Act: -0.1700
Data Index: 4881606 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1898. Min Act: -0.1700
Data Index: 6072000 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1898. Min Act: -0.1700
Data Index: 1913156 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1583. Min Act: -0.1700
Data Index: 7578172 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1426. Min Act: -0.1700
Data Index: 2324537 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.0953. Min Act: -0.1700
Data Index: 4240126 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1111. Min Act: -0.1700
Data Index: 3292026 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1269. Min Act: -0.1700
Data Index: 3574261 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1426. Min Act: -0.1700
Data Index: 6157208 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1111. Min Act: -0.1700
Data Index: 87740 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1111. Min Act: -0.1700
Data Index: 3909742 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4410. Min Range: -3.4410
Max Act: 3.1111. Min Act: -0.1700
Data Index: 3064260 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19