Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.6220. Min Act: -0.1700
Data Index: 5899320 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.4032. Min Act: -0.1700
Data Index: 703836 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.3407. Min Act: -0.1700
Data Index: 7327266 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.2782. Min Act: -0.1700
Data Index: 5212107 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.2470. Min Act: -0.1700
Data Index: 8129295 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.2470. Min Act: -0.1700
Data Index: 6194252 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.2470. Min Act: -0.1700
Data Index: 5336136 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.2157. Min Act: -0.1700
Data Index: 5899316 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.1845. Min Act: -0.1700
Data Index: 15445 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.1845. Min Act: -0.1700
Data Index: 5999173 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.1532. Min Act: -0.1700
Data Index: 703837 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0907. Min Act: -0.1700
Data Index: 3078702 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0907. Min Act: -0.1700
Data Index: 3731083 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0907. Min Act: -0.1700
Data Index: 1020148 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0595. Min Act: -0.1700
Data Index: 8596260 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0595. Min Act: -0.1700
Data Index: 2963338 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0595. Min Act: -0.1700
Data Index: 6396888 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0595. Min Act: -0.1700
Data Index: 8734405 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0282. Min Act: -0.1700
Data Index: 5560231 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6220. Min Range: -5.6220
Max Act: 5.0282. Min Act: -0.1700
Data Index: 8425490 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19