Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4096. Min Range: -7.4096
Max Act: 7.4096. Min Act: -0.1700
Data Index: 7692495 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4096. Min Range: -7.4096
Max Act: 7.2534. Min Act: -0.1700
Data Index: 7692490 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4096. Min Range: -7.4096
Max Act: 7.0971. Min Act: -0.1700
Data Index: 7692493 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4096. Min Range: -7.4096
Max Act: 7.0971. Min Act: -0.1700
Data Index: 7692498 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4096. Min Range: -7.4096
Max Act: 7.0034. Min Act: -0.1700
Data Index: 8047904 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4096. Min Range: -7.4096
Max Act: 7.0034. Min Act: -0.1700
Data Index: 7672968 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.9721. Min Act: -0.1700
Data Index: 1417176 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.9096. Min Act: -0.1700
Data Index: 7692496 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.8159. Min Act: -0.1700
Data Index: 7692492 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.7534. Min Act: -0.1700
Data Index: 1417175 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6909. Min Act: -0.1700
Data Index: 2444764 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6596. Min Act: -0.1700
Data Index: 6216 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6596. Min Act: -0.1700
Data Index: 1738494 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6909. Min Act: -0.1700
Data Index: 5746392 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6284. Min Act: -0.1700
Data Index: 5575957 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6284. Min Act: -0.1700
Data Index: 8442329 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.6284. Min Act: -0.1700
Data Index: 4911959 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.5971. Min Act: -0.1700
Data Index: 2480143 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.5971. Min Act: -0.1700
Data Index: 5857656 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4096. Min Range: -7.4096
Max Act: 6.5971. Min Act: -0.1700
Data Index: 2480141 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19