Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3988 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.4254. Min Act: -0.1700
Data Index: 1495200 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.4078. Min Act: -0.1700
Data Index: 3378109 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.4078. Min Act: -0.1700
Data Index: 1495214 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3902. Min Act: -0.1700
Data Index: 5056235 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3902. Min Act: -0.1700
Data Index: 5056219 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3902. Min Act: -0.1700
Data Index: 6920497 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3725. Min Act: -0.1700
Data Index: 7385253 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 3158815 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 6360741 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3725. Min Act: -0.1700
Data Index: 6209036 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3725. Min Act: -0.1700
Data Index: 5158117 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 8781156 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 8484864 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 8484863 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 4951647 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 4599578 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 7122770 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3549. Min Act: -0.1700
Data Index: 6920479 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3373. Min Act: -0.1700
Data Index: 1443514 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4254. Min Range: -1.4254
Max Act: 1.3373. Min Act: -0.1700
Data Index: 1527121 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19