Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.9331. Min Act: -0.1700
Data Index: 2683517 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.7456. Min Act: -0.1700
Data Index: 8177329 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.7456. Min Act: -0.1700
Data Index: 5247538 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.6206. Min Act: -0.1700
Data Index: 3035129 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.6206. Min Act: -0.1700
Data Index: 7388437 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.5581. Min Act: -0.1700
Data Index: 6266284 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.5581. Min Act: -0.1700
Data Index: 2519875 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4956. Min Act: -0.1700
Data Index: 6160083 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4331. Min Act: -0.1700
Data Index: 1197738 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4956. Min Act: -0.1700
Data Index: 4655913 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4956. Min Act: -0.1700
Data Index: 7460180 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4956. Min Act: -0.1700
Data Index: 3509633 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4956. Min Act: -0.1700
Data Index: 1526285 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4956. Min Act: -0.1700
Data Index: 1834290 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.4331. Min Act: -0.1700
Data Index: 4185955 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.3706. Min Act: -0.1700
Data Index: 3112023 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.3706. Min Act: -0.1700
Data Index: 6400969 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.3706. Min Act: -0.1700
Data Index: 5401181 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.3706. Min Act: -0.1700
Data Index: 1519914 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9331. Min Range: -8.9331
Max Act: 8.2456. Min Act: -0.1700
Data Index: 4290400 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19