Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 261 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0639. Min Range: -5.0639
Max Act: 5.0639. Min Act: -0.1700
Data Index: 3211653 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.9389. Min Act: -0.1700
Data Index: 2269874 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.9076. Min Act: -0.1700
Data Index: 130885 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8764. Min Act: -0.1700
Data Index: 5099007 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8764. Min Act: -0.1700
Data Index: 1802767 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8451. Min Act: -0.1700
Data Index: 6115006 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8451. Min Act: -0.1700
Data Index: 2008442 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8451. Min Act: -0.1700
Data Index: 119460 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8139. Min Act: -0.1700
Data Index: 1753097 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8139. Min Act: -0.1700
Data Index: 8010437 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8139. Min Act: -0.1700
Data Index: 121784 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.8139. Min Act: -0.1700
Data Index: 1726435 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.7826. Min Act: -0.1700
Data Index: 2988851 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.7514. Min Act: -0.1700
Data Index: 4207440 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.7514. Min Act: -0.1700
Data Index: 1460078 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.7514. Min Act: -0.1700
Data Index: 7603004 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.7201. Min Act: -0.1700
Data Index: 145845 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.6889. Min Act: -0.1700
Data Index: 6121756 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.6889. Min Act: -0.1700
Data Index: 1909004 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0639. Min Range: -5.0639
Max Act: 4.6889. Min Act: -0.1700
Data Index: 954828 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19