Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1488 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.8421. Min Act: -0.1700
Data Index: 2315231 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.8421. Min Act: -0.1700
Data Index: 1837560 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.7796. Min Act: -0.1700
Data Index: 3813086 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.6546. Min Act: -0.1700
Data Index: 264323 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.5296. Min Act: -0.1700
Data Index: 8803801 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.5296. Min Act: -0.1700
Data Index: 3264703 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.5296. Min Act: -0.1700
Data Index: 2018987 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.5296. Min Act: -0.1700
Data Index: 3426004 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4046. Min Act: -0.1700
Data Index: 5896209 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4671. Min Act: -0.1700
Data Index: 1520403 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4671. Min Act: -0.1700
Data Index: 1850324 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4671. Min Act: -0.1700
Data Index: 8095466 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.3421. Min Act: -0.1700
Data Index: 2283025 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4046. Min Act: -0.1700
Data Index: 1293394 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.3421. Min Act: -0.1700
Data Index: 2845221 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4046. Min Act: -0.1700
Data Index: 4550076 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4046. Min Act: -0.1700
Data Index: 7388651 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.4046. Min Act: -0.1700
Data Index: 8009833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.2796. Min Act: -0.1700
Data Index: 4393305 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8421. Min Range: -9.8421
Max Act: 9.3421. Min Act: -0.1700
Data Index: 5789496 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19