Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.6237. Min Act: -0.1700
Data Index: 1035814 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.3425. Min Act: -0.1700
Data Index: 55982 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.3112. Min Act: -0.1700
Data Index: 1917763 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.3112. Min Act: -0.1700
Data Index: 5972521 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.2487. Min Act: -0.1700
Data Index: 5735993 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.2175. Min Act: -0.1700
Data Index: 8711497 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.2487. Min Act: -0.1700
Data Index: 88344 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.1862. Min Act: -0.1700
Data Index: 4576529 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.1862. Min Act: -0.1700
Data Index: 7434385 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.1862. Min Act: -0.1700
Data Index: 6114335 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.1550. Min Act: -0.1700
Data Index: 3946131 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.1550. Min Act: -0.1700
Data Index: 425997 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.0925. Min Act: -0.1700
Data Index: 4099606 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.0925. Min Act: -0.1700
Data Index: 388537 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.0925. Min Act: -0.1700
Data Index: 8185217 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.0925. Min Act: -0.1700
Data Index: 1604745 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6237. Min Range: -7.6237
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5561235 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6237. Min Range: -7.6237
Max Act: 6.9362. Min Act: -0.1700
Data Index: 7318128 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6237. Min Range: -7.6237
Max Act: 6.9362. Min Act: -0.1700
Data Index: 7121080 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6237. Min Range: -7.6237
Max Act: 6.9050. Min Act: -0.1700
Data Index: 6448752 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19