Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.5716. Min Act: -0.1700
Data Index: 3621971 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.5091. Min Act: -0.1700
Data Index: 4574218 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.5091. Min Act: -0.1700
Data Index: 7268457 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.4466. Min Act: -0.1700
Data Index: 1027010 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.3528. Min Act: -0.1700
Data Index: 3971135 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.2278. Min Act: -0.1700
Data Index: 2763038 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.2591. Min Act: -0.1700
Data Index: 6849500 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.2903. Min Act: -0.1700
Data Index: 5758898 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.2591. Min Act: -0.1700
Data Index: 4702072 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.2278. Min Act: -0.1700
Data Index: 7350120 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1966. Min Act: -0.1700
Data Index: 6970142 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1966. Min Act: -0.1700
Data Index: 7193502 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1341. Min Act: -0.1700
Data Index: 3129172 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1653. Min Act: -0.1700
Data Index: 4856905 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1966. Min Act: -0.1700
Data Index: 3441119 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1653. Min Act: -0.1700
Data Index: 2147610 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1653. Min Act: -0.1700
Data Index: 3337060 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1653. Min Act: -0.1700
Data Index: 7522157 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1341. Min Act: -0.1700
Data Index: 2684988 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5716. Min Range: -6.5716
Max Act: 6.1341. Min Act: -0.1700
Data Index: 6999745 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19