Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2488 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3587. Min Range: -5.3587
Max Act: 5.3587. Min Act: -0.1696
Data Index: 1741038 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3587. Min Range: -5.3587
Max Act: 5.0774. Min Act: -0.1699
Data Index: 2742850 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.9836. Min Act: -0.1700
Data Index: 7150903 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.9211. Min Act: -0.1700
Data Index: 3803639 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8899. Min Act: -0.1699
Data Index: 5244892 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8586. Min Act: -0.1700
Data Index: 4074187 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8586. Min Act: -0.1700
Data Index: 7274546 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8586. Min Act: -0.1700
Data Index: 7274548 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8274. Min Act: -0.1700
Data Index: 8550882 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8586. Min Act: -0.1700
Data Index: 8261994 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8274. Min Act: -0.1700
Data Index: 7398290 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.8274. Min Act: -0.1700
Data Index: 38717 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7961. Min Act: -0.1700
Data Index: 2592217 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7961. Min Act: -0.1700
Data Index: 6470817 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7961. Min Act: -0.1700
Data Index: 4708950 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7961. Min Act: -0.1700
Data Index: 789964 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7649. Min Act: -0.1700
Data Index: 5302420 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7649. Min Act: -0.1700
Data Index: 7974037 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7649. Min Act: -0.1700
Data Index: 8294100 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3587. Min Range: -5.3587
Max Act: 4.7649. Min Act: -0.1700
Data Index: 4354738 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19