Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.8506. Min Act: -0.1700
Data Index: 2851019 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.6006. Min Act: -0.1700
Data Index: 8600953 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.4756. Min Act: -0.1700
Data Index: 7285593 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.4756. Min Act: -0.1700
Data Index: 1108940 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.1006. Min Act: -0.1700
Data Index: 3602140 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.1631. Min Act: -0.1700
Data Index: 1680380 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8506. Min Range: -11.8506
Max Act: 11.1631. Min Act: -0.1700
Data Index: 4351161 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.9756. Min Act: -0.1700
Data Index: 8733520 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.8506. Min Act: -0.1700
Data Index: 5221591 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.7881. Min Act: -0.1700
Data Index: 1464844 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.7256. Min Act: -0.1700
Data Index: 3480147 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.6631. Min Act: -0.1700
Data Index: 6512550 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.6006. Min Act: -0.1700
Data Index: 5292867 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.5381. Min Act: -0.1700
Data Index: 318694 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.4756. Min Act: -0.1700
Data Index: 6495831 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.4756. Min Act: -0.1700
Data Index: 6034886 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.4131. Min Act: -0.1700
Data Index: 6336626 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.2881. Min Act: -0.1700
Data Index: 586132 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.2881. Min Act: -0.1700
Data Index: 2703278 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8506. Min Range: -11.8506
Max Act: 10.2256. Min Act: -0.1699
Data Index: 8042735 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19