Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4739 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.6021. Min Act: -0.1700
Data Index: 2513504 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.5709. Min Act: -0.1700
Data Index: 75580 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.5709. Min Act: -0.1700
Data Index: 216887 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4771. Min Act: -0.1700
Data Index: 1102253 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4459. Min Act: -0.1700
Data Index: 6633416 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4771. Min Act: -0.1700
Data Index: 251472 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 1079435 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4459. Min Act: -0.1700
Data Index: 1208679 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4459. Min Act: -0.1700
Data Index: 7064871 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4459. Min Act: -0.1700
Data Index: 7235119 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4459. Min Act: -0.1700
Data Index: 7494234 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 3794226 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 8383439 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 4813689 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 5763850 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 7308357 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 1079437 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 506395 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 6583097 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6021. Min Range: -4.6021
Max Act: 4.4146. Min Act: -0.1700
Data Index: 6396383 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19