Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4896 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.7639. Min Act: -0.1700
Data Index: 6657427 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.7639. Min Act: -0.1700
Data Index: 7815921 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.7639. Min Act: -0.1700
Data Index: 5995470 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.7639. Min Act: -0.1700
Data Index: 6351864 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.7327. Min Act: -0.1700
Data Index: 4606162 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.6702. Min Act: -0.1700
Data Index: 7327947 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.6077. Min Act: -0.1700
Data Index: 4746250 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.5764. Min Act: -0.1700
Data Index: 5982993 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.5452. Min Act: -0.1700
Data Index: 3541187 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.5452. Min Act: -0.1700
Data Index: 744074 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.5139. Min Act: -0.1700
Data Index: 5385770 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.5139. Min Act: -0.1700
Data Index: 793017 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7032385 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4514. Min Act: -0.1700
Data Index: 5135993 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4827. Min Act: -0.1700
Data Index: 6958121 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4514. Min Act: -0.1700
Data Index: 1404023 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4514. Min Act: -0.1700
Data Index: 4926770 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4514. Min Act: -0.1700
Data Index: 1055833 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4514. Min Act: -0.1700
Data Index: 1712272 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7639. Min Range: -5.7639
Max Act: 5.4202. Min Act: -0.1700
Data Index: 828419 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19