Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.7344. Min Act: -0.1700
Data Index: 6313304 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.7032. Min Act: -0.1700
Data Index: 7360625 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.6407. Min Act: -0.1700
Data Index: 3980173 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5469. Min Act: -0.1700
Data Index: 459357 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5782. Min Act: -0.1700
Data Index: 6313314 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5469. Min Act: -0.1700
Data Index: 831447 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5469. Min Act: -0.1700
Data Index: 1091126 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5469. Min Act: -0.1700
Data Index: 72435 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5157. Min Act: -0.1700
Data Index: 6431376 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5157. Min Act: -0.1700
Data Index: 5603444 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4844. Min Act: -0.1700
Data Index: 2046109 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5157. Min Act: -0.1700
Data Index: 3416409 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4844. Min Act: -0.1700
Data Index: 4590435 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.5157. Min Act: -0.1700
Data Index: 4145852 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4532. Min Act: -0.1700
Data Index: 7109025 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4532. Min Act: -0.1700
Data Index: 7782180 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4219. Min Act: -0.1700
Data Index: 6398677 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4532. Min Act: -0.1700
Data Index: 4708260 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4532. Min Act: -0.1700
Data Index: 2152813 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7344. Min Range: -4.7344
Max Act: 4.4532. Min Act: -0.1700
Data Index: 2659839 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19