Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5946 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.9309. Min Act: -0.1700
Data Index: 6057175 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.8371. Min Act: -0.1700
Data Index: 1703217 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.8059. Min Act: -0.1700
Data Index: 1327129 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7746. Min Act: -0.1700
Data Index: 4233784 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 8217087 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7434. Min Act: -0.1700
Data Index: 626632 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 8350668 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7434. Min Act: -0.1700
Data Index: 2628544 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 5249897 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6809. Min Act: -0.1700
Data Index: 3578837 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 7432547 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 8331107 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 5535319 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.7121. Min Act: -0.1700
Data Index: 6804602 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6496. Min Act: -0.1700
Data Index: 8331109 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6496. Min Act: -0.1700
Data Index: 3978893 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6496. Min Act: -0.1700
Data Index: 2189338 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6496. Min Act: -0.1700
Data Index: 311507 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6496. Min Act: -0.1700
Data Index: 626633 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9309. Min Range: -4.9309
Max Act: 4.6496. Min Act: -0.1700
Data Index: 4733740 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19