Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1158 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.5410. Min Act: -0.1700
Data Index: 7581799 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4784. Min Act: -0.1700
Data Index: 1169021 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.5097. Min Act: -0.1700
Data Index: 754925 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4784. Min Act: -0.1700
Data Index: 4787393 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4470. Min Act: -0.1700
Data Index: 5658864 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4157. Min Act: -0.1700
Data Index: 8384708 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4314. Min Act: -0.1700
Data Index: 8397338 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4000. Min Act: -0.1700
Data Index: 5318713 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4784. Min Act: -0.1700
Data Index: 2080386 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4314. Min Act: -0.1700
Data Index: 6305857 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4470. Min Act: -0.1700
Data Index: 3331263 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4000. Min Act: -0.1700
Data Index: 5294463 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4000. Min Act: -0.1700
Data Index: 5669568 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.3216. Min Act: -0.1700
Data Index: 7067898 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.3843. Min Act: -0.1700
Data Index: 2921369 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.3687. Min Act: -0.1700
Data Index: 7637360 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.4000. Min Act: -0.1700
Data Index: 8758906 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.3530. Min Act: -0.1700
Data Index: 2984787 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.3843. Min Act: -0.1700
Data Index: 3600089 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5410. Min Range: -3.5410
Max Act: 3.3530. Min Act: -0.1700
Data Index: 7724600 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19