Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4685536 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.3922. Min Act: -0.1700
Data Index: 4685538 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.2985. Min Act: -0.1700
Data Index: 897648 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.2672. Min Act: -0.1700
Data Index: 6794393 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.2360. Min Act: -0.1700
Data Index: 4064577 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.2672. Min Act: -0.1700
Data Index: 7538468 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2248785 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.2047. Min Act: -0.1700
Data Index: 704185 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.1735. Min Act: -0.1700
Data Index: 6569842 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.1110. Min Act: -0.1700
Data Index: 7311577 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.1110. Min Act: -0.1700
Data Index: 7800472 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.0797. Min Act: -0.1700
Data Index: 8773962 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.0485. Min Act: -0.1700
Data Index: 1925866 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.0172. Min Act: -0.1700
Data Index: 2401030 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4547. Min Range: -5.4547
Max Act: 5.0172. Min Act: -0.1700
Data Index: 6545292 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4547. Min Range: -5.4547
Max Act: 4.9547. Min Act: -0.1700
Data Index: 830039 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4547. Min Range: -5.4547
Max Act: 4.9860. Min Act: -0.1700
Data Index: 1176732 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4547. Min Range: -5.4547
Max Act: 4.9860. Min Act: -0.1700
Data Index: 7003647 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4547. Min Range: -5.4547
Max Act: 4.9860. Min Act: -0.1700
Data Index: 8686252 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4547. Min Range: -5.4547
Max Act: 4.9547. Min Act: -0.1700
Data Index: 2401031 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19