Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.4770. Min Act: -0.1700
Data Index: 7429171 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.2895. Min Act: -0.1700
Data Index: 4069075 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1958. Min Act: -0.1700
Data Index: 748160 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1645. Min Act: -0.1700
Data Index: 7078221 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.1020. Min Act: -0.1700
Data Index: 6323664 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.0395. Min Act: -0.1700
Data Index: 1529525 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.0395. Min Act: -0.1700
Data Index: 5503415 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4770. Min Range: -5.4770
Max Act: 5.0083. Min Act: -0.1700
Data Index: 4282709 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.9770. Min Act: -0.1700
Data Index: 564385 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.9770. Min Act: -0.1700
Data Index: 2013108 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.9458. Min Act: -0.1700
Data Index: 4342315 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.9458. Min Act: -0.1700
Data Index: 313057 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.9458. Min Act: -0.1700
Data Index: 6930553 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.9145. Min Act: -0.1700
Data Index: 4003051 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.8833. Min Act: -0.1700
Data Index: 8563934 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.8833. Min Act: -0.1700
Data Index: 6156360 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.8833. Min Act: -0.1700
Data Index: 4700355 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.8833. Min Act: -0.1700
Data Index: 1253899 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.8520. Min Act: -0.1700
Data Index: 1908544 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4770. Min Range: -5.4770
Max Act: 4.8520. Min Act: -0.1700
Data Index: 4508684 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19