Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1038 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.3460. Min Act: -0.1700
Data Index: 4938448 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1898. Min Act: -0.1700
Data Index: 8208825 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1898. Min Act: -0.1700
Data Index: 7545738 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0960. Min Act: -0.1700
Data Index: 803996 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0335. Min Act: -0.1700
Data Index: 4223504 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0022. Min Act: -0.1700
Data Index: 5255292 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0022. Min Act: -0.1700
Data Index: 5886208 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0022. Min Act: -0.1700
Data Index: 3195831 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0335. Min Act: -0.1700
Data Index: 6855983 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9710. Min Act: -0.1700
Data Index: 5835253 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 3888540 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9710. Min Act: -0.1700
Data Index: 7706620 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 1359166 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 6734285 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 1220270 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 8212409 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9084. Min Act: -0.1700
Data Index: 3850682 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 803994 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9084. Min Act: -0.1700
Data Index: 1429996 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9397. Min Act: -0.1700
Data Index: 5781826 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19