Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1434 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.3424. Min Act: -0.1700
Data Index: 2986690 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2799. Min Act: -0.1700
Data Index: 4231900 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.3112. Min Act: -0.1700
Data Index: 2573264 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2799. Min Act: -0.1700
Data Index: 5352095 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2487. Min Act: -0.1700
Data Index: 8462798 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2174. Min Act: -0.1700
Data Index: 6434752 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2487. Min Act: -0.1700
Data Index: 5398687 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2174. Min Act: -0.1700
Data Index: 1159360 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2487. Min Act: -0.1700
Data Index: 2281260 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2174. Min Act: -0.1700
Data Index: 2410132 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2174. Min Act: -0.1700
Data Index: 1692734 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2174. Min Act: -0.1700
Data Index: 5352093 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1862. Min Act: -0.1700
Data Index: 349556 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.2174. Min Act: -0.1700
Data Index: 6771438 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1549. Min Act: -0.1700
Data Index: 4452151 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1862. Min Act: -0.1700
Data Index: 8135642 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1862. Min Act: -0.1700
Data Index: 5352110 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1862. Min Act: -0.1700
Data Index: 7844316 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1862. Min Act: -0.1700
Data Index: 7356944 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3424. Min Range: -4.3424
Max Act: 4.1862. Min Act: -0.1700
Data Index: 3262258 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19