Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4551 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.3900. Min Act: -0.1700
Data Index: 659747 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.4525. Min Act: -0.1700
Data Index: 5820355 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.2650. Min Act: -0.1700
Data Index: 1043324 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.2650. Min Act: -0.1700
Data Index: 4856092 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.2650. Min Act: -0.1700
Data Index: 6731616 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.1400. Min Act: -0.1700
Data Index: 3685477 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.0150. Min Act: -0.1700
Data Index: 4293748 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4525. Min Range: -11.4525
Max Act: 11.0150. Min Act: -0.1700
Data Index: 610341 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8900. Min Act: -0.1700
Data Index: 7261593 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8900. Min Act: -0.1700
Data Index: 3825660 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8900. Min Act: -0.1700
Data Index: 6210487 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8275. Min Act: -0.1700
Data Index: 1675575 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8275. Min Act: -0.1700
Data Index: 7184829 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8275. Min Act: -0.1700
Data Index: 3318135 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.8275. Min Act: -0.1700
Data Index: 1205405 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.7650. Min Act: -0.1700
Data Index: 1814089 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.7650. Min Act: -0.1700
Data Index: 4918854 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.7025. Min Act: -0.1700
Data Index: 6201428 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.7650. Min Act: -0.1700
Data Index: 2638378 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4525. Min Range: -11.4525
Max Act: 10.6400. Min Act: -0.1700
Data Index: 5537312 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19