Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5147 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.8525. Min Act: -0.1700
Data Index: 7680651 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.8212. Min Act: -0.1700
Data Index: 5726882 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.8212. Min Act: -0.1700
Data Index: 5726889 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.8212. Min Act: -0.1700
Data Index: 2752898 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.7900. Min Act: -0.1700
Data Index: 7864511 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.7900. Min Act: -0.1700
Data Index: 4807928 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.7587. Min Act: -0.1700
Data Index: 8716333 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.7275. Min Act: -0.1700
Data Index: 1398437 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6962. Min Act: -0.1700
Data Index: 2569466 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6962. Min Act: -0.1700
Data Index: 18686 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6650. Min Act: -0.1700
Data Index: 7253385 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6337. Min Act: -0.1700
Data Index: 1294150 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6337. Min Act: -0.1700
Data Index: 7527574 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 5726888 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 666672 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 2049695 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 8774320 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 8825563 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 8020892 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8525. Min Range: -4.8525
Max Act: 4.6024. Min Act: -0.1700
Data Index: 3431279 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19