Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4192 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0815. Min Range: -10.0815
Max Act: 10.0815. Min Act: -0.1700
Data Index: 4745104 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.6440. Min Act: -0.1700
Data Index: 3674321 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.5815. Min Act: -0.1700
Data Index: 4646815 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.5190. Min Act: -0.1700
Data Index: 4266517 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.3940. Min Act: -0.1700
Data Index: 7414295 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.4565. Min Act: -0.1700
Data Index: 164338 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.3940. Min Act: -0.1700
Data Index: 8050615 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.3315. Min Act: -0.1700
Data Index: 1769663 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.2690. Min Act: -0.1700
Data Index: 4503132 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.2065. Min Act: -0.1700
Data Index: 8810364 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.2065. Min Act: -0.1700
Data Index: 5674667 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0815. Min Act: -0.1700
Data Index: 6928073 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.1440. Min Act: -0.1700
Data Index: 77318 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.1440. Min Act: -0.1700
Data Index: 6998576 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0190. Min Act: -0.1700
Data Index: 3844484 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0190. Min Act: -0.1700
Data Index: 5488857 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0190. Min Act: -0.1700
Data Index: 6186760 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0190. Min Act: -0.1700
Data Index: 4582761 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0190. Min Act: -0.1700
Data Index: 1233094 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0815. Min Range: -10.0815
Max Act: 9.0190. Min Act: -0.1700
Data Index: 1443261 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19