Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1830. Min Range: -9.1830
Max Act: 9.1830. Min Act: -0.1700
Data Index: 2851089 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1830. Min Range: -9.1830
Max Act: 9.1830. Min Act: -0.1700
Data Index: 6150463 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1830. Min Range: -9.1830
Max Act: 9.0580. Min Act: -0.1700
Data Index: 6425673 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.9955. Min Act: -0.1700
Data Index: 7709264 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1830. Min Range: -9.1830
Max Act: 9.0580. Min Act: -0.1700
Data Index: 4614804 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.9955. Min Act: -0.1700
Data Index: 3750652 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1830. Min Range: -9.1830
Max Act: 9.0580. Min Act: -0.1700
Data Index: 7344222 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1830. Min Range: -9.1830
Max Act: 9.0580. Min Act: -0.1700
Data Index: 893102 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 4298850 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.9330. Min Act: -0.1700
Data Index: 1985235 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 548253 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 1445137 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 4468591 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 5420620 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 2495424 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8705. Min Act: -0.1700
Data Index: 2033565 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8080. Min Act: -0.1700
Data Index: 6906677 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8080. Min Act: -0.1700
Data Index: 6150473 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.8080. Min Act: -0.1700
Data Index: 4196627 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1830. Min Range: -9.1830
Max Act: 8.7455. Min Act: -0.1700
Data Index: 4815023 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19