Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.4611. Min Act: -0.1700
Data Index: 8321951 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.3986. Min Act: -0.1700
Data Index: 3437465 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.3674. Min Act: -0.1700
Data Index: 6347269 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.3048. Min Act: -0.1700
Data Index: 4616233 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2111. Min Act: -0.1700
Data Index: 1342477 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2736. Min Act: -0.1700
Data Index: 5180315 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2423. Min Act: -0.1700
Data Index: 2180786 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2111. Min Act: -0.1700
Data Index: 800371 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2111. Min Act: -0.1700
Data Index: 3803000 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.1798. Min Act: -0.1700
Data Index: 2596495 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2423. Min Act: -0.1700
Data Index: 1647352 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2423. Min Act: -0.1700
Data Index: 5991309 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2423. Min Act: -0.1700
Data Index: 7823179 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2111. Min Act: -0.1700
Data Index: 8112307 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2423. Min Act: -0.1700
Data Index: 5578816 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.1798. Min Act: -0.1700
Data Index: 4701586 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.1798. Min Act: -0.1700
Data Index: 3832924 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.1798. Min Act: -0.1700
Data Index: 2180916 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.1798. Min Act: -0.1700
Data Index: 4360791 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4611. Min Range: -4.4611
Max Act: 4.2111. Min Act: -0.1700
Data Index: 393389 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19