Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2163 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2317. Min Range: -6.2317
Max Act: 4.1379. Min Act: -0.1700
Data Index: 966437 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2317. Min Range: -6.2317
Max Act: 6.2317. Min Act: -0.1700
Data Index: 3788228 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2317. Min Range: -6.2317
Max Act: 4.8254. Min Act: -0.1700
Data Index: 6837840 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2317. Min Range: -6.2317
Max Act: 3.9034. Min Act: -0.1700
Data Index: 966440 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.5442. Min Act: -0.1700
Data Index: 6457777 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.9817. Min Act: -0.1700
Data Index: 3478866 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.7004. Min Act: -0.1700
Data Index: 166576 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.2942. Min Act: -0.1700
Data Index: 8221946 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2317. Min Range: -6.2317
Max Act: 4.8567. Min Act: -0.1700
Data Index: 1135910 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.9192. Min Act: -0.1700
Data Index: 6062424 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.9192. Min Act: -0.1700
Data Index: 8578877 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7658782 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.8879. Min Act: -0.1700
Data Index: 4926076 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.9192. Min Act: -0.1700
Data Index: 8637398 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.8879. Min Act: -0.1700
Data Index: 372539 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.7629. Min Act: -0.1700
Data Index: 384794 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.7942. Min Act: -0.1700
Data Index: 6231446 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.7317. Min Act: -0.1700
Data Index: 4008830 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.7942. Min Act: -0.1700
Data Index: 1912223 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2317. Min Range: -6.2317
Max Act: 5.7629. Min Act: -0.1700
Data Index: 7040036 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19