Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.8654. Min Act: -0.1700
Data Index: 4707742 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.8341. Min Act: -0.1700
Data Index: 7572608 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.7716. Min Act: -0.1700
Data Index: 2950190 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.7716. Min Act: -0.1700
Data Index: 8053754 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.7091. Min Act: -0.1700
Data Index: 7670622 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.7404. Min Act: -0.1700
Data Index: 8155691 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.7091. Min Act: -0.1700
Data Index: 2775360 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.7091. Min Act: -0.1700
Data Index: 7090993 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.6466. Min Act: -0.1700
Data Index: 252377 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.6466. Min Act: -0.1700
Data Index: 1516851 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.6466. Min Act: -0.1700
Data Index: 3163038 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.6466. Min Act: -0.1700
Data Index: 8610099 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2440534 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5529. Min Act: -0.1700
Data Index: 4270315 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5841. Min Act: -0.1700
Data Index: 574726 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5841. Min Act: -0.1700
Data Index: 6340194 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5529. Min Act: -0.1700
Data Index: 2993642 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5841. Min Act: -0.1700
Data Index: 403811 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5841. Min Act: -0.1700
Data Index: 5974044 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8654. Min Range: -5.8654
Max Act: 5.5841. Min Act: -0.1700
Data Index: 1642574 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19