Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 481 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.6264. Min Act: -0.1700
Data Index: 3099941 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5741. Min Act: -0.1700
Data Index: 743414 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5653. Min Act: -0.1700
Data Index: 318852 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5566. Min Act: -0.1700
Data Index: 8536938 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5303. Min Act: -0.1700
Data Index: 4136610 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5390. Min Act: -0.1700
Data Index: 1085145 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5303. Min Act: -0.1700
Data Index: 2366387 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5303. Min Act: -0.1700
Data Index: 4683554 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5215. Min Act: -0.1700
Data Index: 5857606 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5215. Min Act: -0.1700
Data Index: 236764 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5215. Min Act: -0.1700
Data Index: 204180 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5215. Min Act: -0.1700
Data Index: 884107 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5040. Min Act: -0.1700
Data Index: 6720478 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5127. Min Act: -0.1700
Data Index: 6422507 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5127. Min Act: -0.1700
Data Index: 758741 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5040. Min Act: -0.1700
Data Index: 5927004 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5040. Min Act: -0.1700
Data Index: 254254 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5127. Min Act: -0.1700
Data Index: 4360317 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.4952. Min Act: -0.1700
Data Index: 5145938 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6264. Min Range: -1.6264
Max Act: 1.5040. Min Act: -0.1700
Data Index: 1671194 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19