Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.4047. Min Act: -0.1700
Data Index: 3681630 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.3110. Min Act: -0.1700
Data Index: 540068 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4335519 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4336662 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2797. Min Act: -0.1700
Data Index: 4495475 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2797. Min Act: -0.1700
Data Index: 6263191 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2172. Min Act: -0.1700
Data Index: 451720 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.2172. Min Act: -0.1700
Data Index: 8576003 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1860. Min Act: -0.1700
Data Index: 5637022 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1860. Min Act: -0.1700
Data Index: 5532897 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1860. Min Act: -0.1700
Data Index: 1054884 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1860. Min Act: -0.1700
Data Index: 6411713 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1860. Min Act: -0.1700
Data Index: 8654767 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1547. Min Act: -0.1700
Data Index: 2503866 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1547. Min Act: -0.1700
Data Index: 6581632 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1860. Min Act: -0.1700
Data Index: 3309629 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1235. Min Act: -0.1700
Data Index: 2318221 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1235. Min Act: -0.1700
Data Index: 1467207 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1235. Min Act: -0.1700
Data Index: 840468 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4047. Min Range: -6.4047
Max Act: 6.1235. Min Act: -0.1700
Data Index: 4281869 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19