Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.8306. Min Act: -0.1700
Data Index: 5937926 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7441282 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.7056. Min Act: -0.1700
Data Index: 7610877 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.6743. Min Act: -0.1700
Data Index: 8660715 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.6118. Min Act: -0.1700
Data Index: 8792423 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.6118. Min Act: -0.1700
Data Index: 7755353 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.6118. Min Act: -0.1700
Data Index: 2912243 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.6118. Min Act: -0.1700
Data Index: 7368228 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5806. Min Act: -0.1700
Data Index: 5665454 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5806. Min Act: -0.1700
Data Index: 5776845 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5806. Min Act: -0.1700
Data Index: 4360843 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5493. Min Act: -0.1700
Data Index: 4355192 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5493. Min Act: -0.1700
Data Index: 7888090 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5181. Min Act: -0.1700
Data Index: 57475 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5181. Min Act: -0.1700
Data Index: 7106063 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5181. Min Act: -0.1700
Data Index: 2075337 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5181. Min Act: -0.1700
Data Index: 8618277 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.5181. Min Act: -0.1700
Data Index: 1297183 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.4868. Min Act: -0.1700
Data Index: 7967375 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8306. Min Range: -4.8306
Max Act: 4.4868. Min Act: -0.1700
Data Index: 1553767 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19