Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2115 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.7652. Min Act: -0.1700
Data Index: 4131534 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.3902. Min Act: -0.1700
Data Index: 486577 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.2339. Min Act: -0.1700
Data Index: 4932708 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.2027. Min Act: -0.1700
Data Index: 7556194 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.1402. Min Act: -0.1700
Data Index: 2173680 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.1402. Min Act: -0.1700
Data Index: 6433306 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.1089. Min Act: -0.1700
Data Index: 3631950 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.1089. Min Act: -0.1700
Data Index: 5166536 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0777. Min Act: -0.1700
Data Index: 4013353 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0777. Min Act: -0.1700
Data Index: 4423371 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0777. Min Act: -0.1700
Data Index: 8551032 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0152. Min Act: -0.1700
Data Index: 3233429 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0464. Min Act: -0.1700
Data Index: 8699001 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0464. Min Act: -0.1700
Data Index: 6816955 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0464. Min Act: -0.1700
Data Index: 3527992 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0464. Min Act: -0.1700
Data Index: 8533017 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0464. Min Act: -0.1700
Data Index: 3702413 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7652. Min Range: -6.7652
Max Act: 6.0464. Min Act: -0.1700
Data Index: 5113837 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7652. Min Range: -6.7652
Max Act: 5.9839. Min Act: -0.1700
Data Index: 4706362 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7652. Min Range: -6.7652
Max Act: 5.9839. Min Act: -0.1700
Data Index: 2598432 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19