Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.9945. Min Act: -0.1700
Data Index: 4792765 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.6195. Min Act: -0.1700
Data Index: 6027161 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.5570. Min Act: -0.1700
Data Index: 2061823 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.4945. Min Act: -0.1700
Data Index: 2061824 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.4945. Min Act: -0.1700
Data Index: 19086 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.3070. Min Act: -0.1700
Data Index: 4464178 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.3695. Min Act: -0.1700
Data Index: 977545 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.2445. Min Act: -0.1700
Data Index: 7338860 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1820. Min Act: -0.1700
Data Index: 4308228 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1820. Min Act: -0.1700
Data Index: 1550281 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1195. Min Act: -0.1700
Data Index: 3578202 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1195. Min Act: -0.1700
Data Index: 2000505 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1195. Min Act: -0.1700
Data Index: 3855032 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1195. Min Act: -0.1700
Data Index: 1358353 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1820. Min Act: -0.1700
Data Index: 7846120 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.1195. Min Act: -0.1700
Data Index: 7345655 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.0258. Min Act: -0.1700
Data Index: 5440755 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.0570. Min Act: -0.1700
Data Index: 6231915 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9945. Min Range: -8.9945
Max Act: 8.0570. Min Act: -0.1700
Data Index: 7370627 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9945. Min Range: -8.9945
Max Act: 7.9945. Min Act: -0.1700
Data Index: 359843 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19