Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.2510. Min Act: -0.1700
Data Index: 8796594 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.1885. Min Act: -0.1700
Data Index: 6537540 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.1260. Min Act: -0.1700
Data Index: 2119120 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.0948. Min Act: -0.1700
Data Index: 7522583 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.0635. Min Act: -0.1700
Data Index: 5800239 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.0010. Min Act: -0.1700
Data Index: 1451952 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9698. Min Act: -0.1700
Data Index: 700560 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2510. Min Range: -5.2510
Max Act: 5.0010. Min Act: -0.1700
Data Index: 2063237 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9698. Min Act: -0.1700
Data Index: 5254662 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9385. Min Act: -0.1700
Data Index: 8814952 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9385. Min Act: -0.1700
Data Index: 8115067 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9385. Min Act: -0.1700
Data Index: 3122251 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9385. Min Act: -0.1700
Data Index: 4014252 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9073. Min Act: -0.1700
Data Index: 8310854 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9073. Min Act: -0.1700
Data Index: 4731391 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.9073. Min Act: -0.1700
Data Index: 167057 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.8760. Min Act: -0.1700
Data Index: 4199552 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.8448. Min Act: -0.1700
Data Index: 651549 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.8760. Min Act: -0.1700
Data Index: 3566196 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2510. Min Range: -5.2510
Max Act: 4.8760. Min Act: -0.1700
Data Index: 883210 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19