Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5713 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.8295. Min Act: -0.1700
Data Index: 3359384 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.3920. Min Act: -0.1700
Data Index: 2337228 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.2982. Min Act: -0.1700
Data Index: 3788340 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.2982. Min Act: -0.1700
Data Index: 1456148 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.2670. Min Act: -0.1700
Data Index: 2160028 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.1107. Min Act: -0.1700
Data Index: 8061049 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.1107. Min Act: -0.1700
Data Index: 3434146 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0795. Min Act: -0.1700
Data Index: 8394416 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0795. Min Act: -0.1700
Data Index: 7627939 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0482. Min Act: -0.1700
Data Index: 4939403 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0482. Min Act: -0.1700
Data Index: 6003096 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0482. Min Act: -0.1700
Data Index: 8462153 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0170. Min Act: -0.1700
Data Index: 2219595 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8295. Min Range: -6.8295
Max Act: 5.9857. Min Act: -0.1700
Data Index: 2725300 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8295. Min Range: -6.8295
Max Act: 6.0170. Min Act: -0.1700
Data Index: 4291546 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8295. Min Range: -6.8295
Max Act: 5.9545. Min Act: -0.1700
Data Index: 7911696 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8295. Min Range: -6.8295
Max Act: 5.9857. Min Act: -0.1700
Data Index: 5912747 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8295. Min Range: -6.8295
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4928554 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8295. Min Range: -6.8295
Max Act: 5.9545. Min Act: -0.1700
Data Index: 571027 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8295. Min Range: -6.8295
Max Act: 5.9857. Min Act: -0.1700
Data Index: 1544448 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19