Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3568. Min Act: -0.1700
Data Index: 1140595 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3411. Min Act: -0.1700
Data Index: 7893536 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3411. Min Act: -0.1700
Data Index: 220133 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3254. Min Act: -0.1700
Data Index: 1818802 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3098. Min Act: -0.1700
Data Index: 5609053 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3098. Min Act: -0.1700
Data Index: 5360885 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2784. Min Act: -0.1700
Data Index: 3575934 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2784. Min Act: -0.1700
Data Index: 2863479 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2626. Min Act: -0.1700
Data Index: 5071305 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2626. Min Act: -0.1700
Data Index: 2161834 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 2723373 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 8234160 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2312. Min Act: -0.1700
Data Index: 3969408 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2312. Min Act: -0.1700
Data Index: 2267263 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2155. Min Act: -0.1700
Data Index: 4198333 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 1961686 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2312. Min Act: -0.1700
Data Index: 6512001 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2312. Min Act: -0.1700
Data Index: 7266745 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2155. Min Act: -0.1700
Data Index: 4407978 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2155. Min Act: -0.1700
Data Index: 2100280 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19