Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.7623. Min Act: -0.1700
Data Index: 6723292 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.6061. Min Act: -0.1700
Data Index: 3601805 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.6061. Min Act: -0.1700
Data Index: 5836946 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.6061. Min Act: -0.1700
Data Index: 6480951 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5748. Min Act: -0.1700
Data Index: 8746079 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5748. Min Act: -0.1700
Data Index: 6994780 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.6061. Min Act: -0.1700
Data Index: 3601804 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5748. Min Act: -0.1700
Data Index: 8707214 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5748. Min Act: -0.1700
Data Index: 283292 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5748. Min Act: -0.1700
Data Index: 6480950 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5123. Min Act: -0.1700
Data Index: 3343357 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5436. Min Act: -0.1700
Data Index: 2117731 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5748. Min Act: -0.1700
Data Index: 5836945 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5436. Min Act: -0.1700
Data Index: 6124961 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5123. Min Act: -0.1700
Data Index: 4136998 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5123. Min Act: -0.1700
Data Index: 2036489 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.4811. Min Act: -0.1700
Data Index: 7209044 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.4811. Min Act: -0.1700
Data Index: 5166774 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5123. Min Act: -0.1700
Data Index: 7322360 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7623. Min Range: -5.7623
Max Act: 5.5123. Min Act: -0.1700
Data Index: 5949993 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19