Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1474. Min Range: -7.1474
Max Act: 7.1474. Min Act: -0.1700
Data Index: 3083496 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.9911. Min Act: -0.1700
Data Index: 7768999 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.9286. Min Act: -0.1700
Data Index: 1989325 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.9286. Min Act: -0.1700
Data Index: 7059306 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8349. Min Act: -0.1700
Data Index: 94123 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8661. Min Act: -0.1700
Data Index: 6573734 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8661. Min Act: -0.1700
Data Index: 7857209 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8349. Min Act: -0.1700
Data Index: 94122 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8349. Min Act: -0.1700
Data Index: 3364724 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8036. Min Act: -0.1700
Data Index: 1945347 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.8036. Min Act: -0.1700
Data Index: 3364725 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7724. Min Act: -0.1700
Data Index: 3905430 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7724. Min Act: -0.1700
Data Index: 2262371 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7411. Min Act: -0.1700
Data Index: 2679272 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7411. Min Act: -0.1700
Data Index: 317439 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7411. Min Act: -0.1700
Data Index: 6374219 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7411. Min Act: -0.1700
Data Index: 8307435 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.7099. Min Act: -0.1700
Data Index: 2942001 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.6474. Min Act: -0.1700
Data Index: 4754225 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1474. Min Range: -7.1474
Max Act: 6.6161. Min Act: -0.1700
Data Index: 5695704 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19