Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5735 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6899. Min Act: -0.1700
Data Index: 700534 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6274. Min Act: -0.1700
Data Index: 1057488 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.5649. Min Act: -0.1700
Data Index: 5761281 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.3774. Min Act: -0.1700
Data Index: 1057490 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.3774. Min Act: -0.1700
Data Index: 5689615 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.2524. Min Act: -0.1700
Data Index: 8228889 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.1899. Min Act: -0.1700
Data Index: 1660507 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0649. Min Act: -0.1700
Data Index: 5078104 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0024. Min Act: -0.1700
Data Index: 5410399 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6899. Min Range: -9.6899
Max Act: 8.9399. Min Act: -0.1700
Data Index: 4078075 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0024. Min Act: -0.1700
Data Index: 2250826 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0024. Min Act: -0.1700
Data Index: 5601538 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0024. Min Act: -0.1700
Data Index: 3469566 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0024. Min Act: -0.1700
Data Index: 6568719 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.0024. Min Act: -0.1700
Data Index: 8254500 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6899. Min Range: -9.6899
Max Act: 8.9399. Min Act: -0.1700
Data Index: 1495202 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6899. Min Range: -9.6899
Max Act: 8.9399. Min Act: -0.1700
Data Index: 2880873 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6899. Min Range: -9.6899
Max Act: 8.9399. Min Act: -0.1700
Data Index: 3986765 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6899. Min Range: -9.6899
Max Act: 8.9399. Min Act: -0.1700
Data Index: 7477416 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6899. Min Range: -9.6899
Max Act: 8.9399. Min Act: -0.1700
Data Index: 2580116 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19