Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0650. Min Range: -7.0650
Max Act: 7.0650. Min Act: -0.1700
Data Index: 435354 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0650. Min Range: -7.0650
Max Act: 7.0025. Min Act: -0.1700
Data Index: 8132058 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.9712. Min Act: -0.1700
Data Index: 7277988 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.9400. Min Act: -0.1700
Data Index: 5626241 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.8462. Min Act: -0.1700
Data Index: 6345752 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.7212. Min Act: -0.1700
Data Index: 7545025 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.6587. Min Act: -0.1700
Data Index: 3828700 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.6587. Min Act: -0.1700
Data Index: 4460231 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.6275. Min Act: -0.1700
Data Index: 2816856 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.6275. Min Act: -0.1700
Data Index: 8132056 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5962. Min Act: -0.1700
Data Index: 539115 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5962. Min Act: -0.1700
Data Index: 8754380 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5650. Min Act: -0.1700
Data Index: 4736431 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5962. Min Act: -0.1700
Data Index: 4491425 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5650. Min Act: -0.1700
Data Index: 4993156 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5337. Min Act: -0.1700
Data Index: 6634006 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5025. Min Act: -0.1700
Data Index: 4460805 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5025. Min Act: -0.1700
Data Index: 1490891 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.5025. Min Act: -0.1700
Data Index: 5380233 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0650. Min Range: -7.0650
Max Act: 6.4712. Min Act: -0.1700
Data Index: 4006997 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19