Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4175 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.7145. Min Act: -0.1700
Data Index: 8420873 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.5895. Min Act: -0.1700
Data Index: 8161158 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.5270. Min Act: -0.1700
Data Index: 1618964 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.4332. Min Act: -0.1700
Data Index: 3398347 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.4020. Min Act: -0.1700
Data Index: 1486563 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.3082. Min Act: -0.1700
Data Index: 8323531 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2770. Min Act: -0.1700
Data Index: 355371 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2770. Min Act: -0.1700
Data Index: 5520698 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2770. Min Act: -0.1700
Data Index: 238822 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2457. Min Act: -0.1700
Data Index: 1047135 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2770. Min Act: -0.1700
Data Index: 7201499 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2770. Min Act: -0.1700
Data Index: 1822800 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2457. Min Act: -0.1700
Data Index: 3454745 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.2145. Min Act: -0.1700
Data Index: 4750947 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.1832. Min Act: -0.1700
Data Index: 685850 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.1832. Min Act: -0.1700
Data Index: 6970885 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.1520. Min Act: -0.1700
Data Index: 6326324 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.1520. Min Act: -0.1700
Data Index: 2920619 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.1207. Min Act: -0.1700
Data Index: 7720666 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7145. Min Range: -6.7145
Max Act: 6.1520. Min Act: -0.1700
Data Index: 585968 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19