Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 633 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.4415. Min Act: -0.1700
Data Index: 3458796 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.3478. Min Act: -0.1700
Data Index: 1299319 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.2228. Min Act: -0.1700
Data Index: 4027582 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.1915. Min Act: -0.1700
Data Index: 1944958 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.1603. Min Act: -0.1700
Data Index: 5717521 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.1290. Min Act: -0.1700
Data Index: 1172843 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.1290. Min Act: -0.1700
Data Index: 3637688 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0978. Min Act: -0.1700
Data Index: 6468023 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0978. Min Act: -0.1700
Data Index: 646249 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0978. Min Act: -0.1700
Data Index: 8428012 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0665. Min Act: -0.1700
Data Index: 5720258 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0353. Min Act: -0.1700
Data Index: 1682475 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0353. Min Act: -0.1700
Data Index: 3711289 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0353. Min Act: -0.1700
Data Index: 5720256 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0353. Min Act: -0.1700
Data Index: 6889629 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4415. Min Range: -6.4415
Max Act: 6.0040. Min Act: -0.1700
Data Index: 1981269 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4415. Min Range: -6.4415
Max Act: 5.9728. Min Act: -0.1700
Data Index: 3379609 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4415. Min Range: -6.4415
Max Act: 5.9728. Min Act: -0.1700
Data Index: 1237893 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4415. Min Range: -6.4415
Max Act: 5.9415. Min Act: -0.1700
Data Index: 1730311 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4415. Min Range: -6.4415
Max Act: 5.9728. Min Act: -0.1700
Data Index: 4998524 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19