Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0285. Min Range: -4.0285
Max Act: 4.0285. Min Act: -0.1700
Data Index: 7410447 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 3884600 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.9660. Min Act: -0.1700
Data Index: 8275303 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8722. Min Act: -0.1700
Data Index: 989191 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8722. Min Act: -0.1700
Data Index: 4663981 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8410. Min Act: -0.1700
Data Index: 7003386 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 2316 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.8097. Min Act: -0.1700
Data Index: 3611060 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7784. Min Act: -0.1700
Data Index: 3948004 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7628. Min Act: -0.1700
Data Index: 6544878 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7315. Min Act: -0.1700
Data Index: 3803648 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7471. Min Act: -0.1700
Data Index: 6064086 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7471. Min Act: -0.1700
Data Index: 3027283 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7315. Min Act: -0.1700
Data Index: 614356 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7315. Min Act: -0.1700
Data Index: 6732987 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7158. Min Act: -0.1700
Data Index: 6492183 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7002. Min Act: -0.1700
Data Index: 8167158 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7158. Min Act: -0.1700
Data Index: 3348603 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.7002. Min Act: -0.1700
Data Index: 1102421 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0285. Min Range: -4.0285
Max Act: 3.6846. Min Act: -0.1700
Data Index: 2083340 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19