Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5350. Min Range: -9.5350
Max Act: 9.5350. Min Act: -0.1700
Data Index: 6972110 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5350. Min Range: -9.5350
Max Act: 9.1600. Min Act: -0.1700
Data Index: 2123954 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5350. Min Range: -9.5350
Max Act: 9.0975. Min Act: -0.1700
Data Index: 3243558 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5350. Min Range: -9.5350
Max Act: 9.0350. Min Act: -0.1700
Data Index: 8551244 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.8475. Min Act: -0.1700
Data Index: 3153765 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.7850. Min Act: -0.1700
Data Index: 428088 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.7225. Min Act: -0.1700
Data Index: 8743360 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.7225. Min Act: -0.1700
Data Index: 5472115 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.6600. Min Act: -0.1700
Data Index: 5820617 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5975. Min Act: -0.1700
Data Index: 704377 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5975. Min Act: -0.1700
Data Index: 7077599 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5975. Min Act: -0.1700
Data Index: 5958031 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5975. Min Act: -0.1700
Data Index: 5059177 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5975. Min Act: -0.1700
Data Index: 1359203 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5350. Min Act: -0.1700
Data Index: 2604108 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5350. Min Act: -0.1700
Data Index: 2356771 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5350. Min Act: -0.1700
Data Index: 4412617 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.4725. Min Act: -0.1700
Data Index: 4015601 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5350. Min Act: -0.1700
Data Index: 3676347 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5350. Min Range: -9.5350
Max Act: 8.5350. Min Act: -0.1700
Data Index: 258146 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19