Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.7499. Min Act: -0.1700
Data Index: 3300840 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.5624. Min Act: -0.1689
Data Index: 572916 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.4374. Min Act: -0.1700
Data Index: 7581741 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.1874. Min Act: -0.1694
Data Index: 8053862 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.1249. Min Act: -0.1689
Data Index: 181692 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.2499. Min Act: -0.1700
Data Index: 7424864 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.1249. Min Act: -0.1700
Data Index: 370291 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.0624. Min Act: -0.1700
Data Index: 3240440 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.0624. Min Act: -0.1700
Data Index: 445623 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.9999. Min Act: -0.1700
Data Index: 6819521 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.9999. Min Act: -0.1697
Data Index: 8380250 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.9374. Min Act: -0.1700
Data Index: 2153238 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7499. Min Range: -10.7499
Max Act: 10.1249. Min Act: -0.1694
Data Index: 2153719 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.9374. Min Act: -0.1700
Data Index: 5635847 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.9374. Min Act: -0.1700
Data Index: 6071696 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.8124. Min Act: -0.1700
Data Index: 2915205 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.8124. Min Act: -0.1699
Data Index: 6850298 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.7499. Min Act: -0.1700
Data Index: 4648631 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.7499. Min Act: -0.1700
Data Index: 1567159 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7499. Min Range: -10.7499
Max Act: 9.7499. Min Act: -0.1700
Data Index: 2709167 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19