Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3485. Min Range: -9.3485
Max Act: 9.3485. Min Act: -0.1700
Data Index: 6399597 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3485. Min Range: -9.3485
Max Act: 9.0360. Min Act: -0.1700
Data Index: 4430675 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.9110. Min Act: -0.1700
Data Index: 7203161 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.9735. Min Act: -0.1700
Data Index: 6696927 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.9110. Min Act: -0.1700
Data Index: 709850 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.8485. Min Act: -0.1700
Data Index: 4599479 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.8485. Min Act: -0.1700
Data Index: 6953489 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7860. Min Act: -0.1700
Data Index: 5923070 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7860. Min Act: -0.1700
Data Index: 6962545 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7860. Min Act: -0.1700
Data Index: 5140160 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7860. Min Act: -0.1700
Data Index: 912270 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7235. Min Act: -0.1700
Data Index: 412852 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7235. Min Act: -0.1700
Data Index: 2600693 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7235. Min Act: -0.1700
Data Index: 5100218 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7235. Min Act: -0.1700
Data Index: 2472716 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.7235. Min Act: -0.1700
Data Index: 8746606 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.6610. Min Act: -0.1700
Data Index: 7701786 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.6610. Min Act: -0.1700
Data Index: 7616143 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.6610. Min Act: -0.1700
Data Index: 4777354 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3485. Min Range: -9.3485
Max Act: 8.5985. Min Act: -0.1700
Data Index: 4448702 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19