Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4687 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.5956. Min Act: -0.1700
Data Index: 545713 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.3456. Min Act: -0.1700
Data Index: 8005671 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 4628271 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2519. Min Act: -0.1700
Data Index: 2853315 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 4794001 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 8791822 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 771286 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1894. Min Act: -0.1700
Data Index: 2159395 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1894. Min Act: -0.1700
Data Index: 2785972 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.2206. Min Act: -0.1700
Data Index: 996211 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1894. Min Act: -0.1700
Data Index: 5731462 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 3053663 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1581. Min Act: -0.1700
Data Index: 3895651 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1581. Min Act: -0.1700
Data Index: 1839899 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 5245770 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 5311155 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.1269. Min Act: -0.1700
Data Index: 5424654 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.0956. Min Act: -0.1700
Data Index: 8624328 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.0956. Min Act: -0.1700
Data Index: 8424420 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5956. Min Range: -7.5956
Max Act: 7.0956. Min Act: -0.1700
Data Index: 4484120 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19