Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5261. Min Range: -7.5261
Max Act: 7.5261. Min Act: -0.1700
Data Index: 764875 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5261. Min Range: -7.5261
Max Act: 7.1511. Min Act: -0.1700
Data Index: 7314407 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5261. Min Range: -7.5261
Max Act: 7.1199. Min Act: -0.1700
Data Index: 5135063 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5261. Min Range: -7.5261
Max Act: 7.0574. Min Act: -0.1700
Data Index: 5806477 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.9636. Min Act: -0.1700
Data Index: 5687037 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.8699. Min Act: -0.1700
Data Index: 6143089 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.9011. Min Act: -0.1700
Data Index: 4570926 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.8386. Min Act: -0.1700
Data Index: 1889854 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.8074. Min Act: -0.1700
Data Index: 3126712 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.7761. Min Act: -0.1700
Data Index: 7032947 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.7449. Min Act: -0.1700
Data Index: 5364601 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.7449. Min Act: -0.1700
Data Index: 2922710 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.7449. Min Act: -0.1700
Data Index: 205076 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.6511. Min Act: -0.1700
Data Index: 5474842 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.6824. Min Act: -0.1700
Data Index: 5474841 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.6511. Min Act: -0.1700
Data Index: 3489239 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.6824. Min Act: -0.1700
Data Index: 1779330 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.6199. Min Act: -0.1700
Data Index: 2417182 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.6199. Min Act: -0.1700
Data Index: 528598 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5261. Min Range: -7.5261
Max Act: 6.5574. Min Act: -0.1700
Data Index: 5237773 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19