Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1141 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.5146. Min Act: -0.1700
Data Index: 5815948 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.4521. Min Act: -0.1700
Data Index: 2657788 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.3583. Min Act: -0.1700
Data Index: 6465601 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.2646. Min Act: -0.1700
Data Index: 5016621 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.1083. Min Act: -0.1700
Data Index: 6850639 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.0771. Min Act: -0.1700
Data Index: 1026009 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.0771. Min Act: -0.1700
Data Index: 4550807 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.9833. Min Act: -0.1700
Data Index: 364387 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5146. Min Range: -6.5146
Max Act: 6.0146. Min Act: -0.1700
Data Index: 8748373 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.9208. Min Act: -0.1700
Data Index: 8539619 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.9521. Min Act: -0.1700
Data Index: 6349689 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.9521. Min Act: -0.1700
Data Index: 858530 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.9208. Min Act: -0.1700
Data Index: 8600816 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.9208. Min Act: -0.1700
Data Index: 4598705 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.8896. Min Act: -0.1700
Data Index: 6701336 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.8583. Min Act: -0.1700
Data Index: 3084261 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.8271. Min Act: -0.1700
Data Index: 8813125 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.7958. Min Act: -0.1700
Data Index: 805821 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.7958. Min Act: -0.1700
Data Index: 1549938 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5146. Min Range: -6.5146
Max Act: 5.7646. Min Act: -0.1700
Data Index: 3586490 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19