Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.7258. Min Act: -0.1700
Data Index: 2443865 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.6617. Min Act: -0.1700
Data Index: 2520329 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.6457. Min Act: -0.1700
Data Index: 5810691 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5975. Min Act: -0.1700
Data Index: 2444191 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.6136. Min Act: -0.1700
Data Index: 5385586 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5814. Min Act: -0.1700
Data Index: 5521170 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5652. Min Act: -0.1700
Data Index: 3899641 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5814. Min Act: -0.1700
Data Index: 2396113 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5652. Min Act: -0.1700
Data Index: 692533 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5491. Min Act: -0.1700
Data Index: 1564234 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5330. Min Act: -0.1700
Data Index: 1989535 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5330. Min Act: -0.1700
Data Index: 1449709 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5168. Min Act: -0.1700
Data Index: 1526027 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5168. Min Act: -0.1700
Data Index: 4830113 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5330. Min Act: -0.1700
Data Index: 7177358 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5006. Min Act: -0.1700
Data Index: 2545741 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5006. Min Act: -0.1700
Data Index: 6397571 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5006. Min Act: -0.1700
Data Index: 4976645 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.4844. Min Act: -0.1700
Data Index: 3002357 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7258. Min Range: -2.7258
Max Act: 2.5006. Min Act: -0.1700
Data Index: 1545560 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19