Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1542. Min Range: -7.1542
Max Act: 7.1542. Min Act: -0.1700
Data Index: 3018147 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.9667. Min Act: -0.1700
Data Index: 4992781 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.8417. Min Act: -0.1700
Data Index: 1762361 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.7167. Min Act: -0.1700
Data Index: 7635708 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.4667. Min Act: -0.1700
Data Index: 8094618 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.4042. Min Act: -0.1700
Data Index: 1959773 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.3729. Min Act: -0.1700
Data Index: 8465531 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.3417. Min Act: -0.1700
Data Index: 7916979 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.3417. Min Act: -0.1700
Data Index: 6422430 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2792. Min Act: -0.1700
Data Index: 398715 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2479. Min Act: -0.1700
Data Index: 1999660 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2479. Min Act: -0.1700
Data Index: 7750058 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2167. Min Act: -0.1700
Data Index: 1500433 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2167. Min Act: -0.1700
Data Index: 8489721 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2167. Min Act: -0.1700
Data Index: 2665684 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.2167. Min Act: -0.1700
Data Index: 7635713 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.1854. Min Act: -0.1700
Data Index: 8107801 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.1854. Min Act: -0.1700
Data Index: 1974139 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.1542. Min Act: -0.1700
Data Index: 3549601 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1542. Min Range: -7.1542
Max Act: 6.1229. Min Act: -0.1700
Data Index: 7635709 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19