Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5799. Min Range: -7.5799
Max Act: 7.5799. Min Act: -0.1700
Data Index: 3522609 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5799. Min Range: -7.5799
Max Act: 7.4237. Min Act: -0.1700
Data Index: 1645395 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5799. Min Range: -7.5799
Max Act: 7.2674. Min Act: -0.1700
Data Index: 2687202 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5799. Min Range: -7.5799
Max Act: 7.1112. Min Act: -0.1700
Data Index: 383057 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5799. Min Range: -7.5799
Max Act: 7.0487. Min Act: -0.1700
Data Index: 4889023 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5799. Min Range: -7.5799
Max Act: 7.0174. Min Act: -0.1700
Data Index: 4857363 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.9549. Min Act: -0.1700
Data Index: 3305735 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.9237. Min Act: -0.1700
Data Index: 3151782 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.9237. Min Act: -0.1700
Data Index: 3940979 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.8612. Min Act: -0.1700
Data Index: 3496630 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.8299. Min Act: -0.1700
Data Index: 5520129 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.7362. Min Act: -0.1700
Data Index: 692424 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.7049. Min Act: -0.1700
Data Index: 4629485 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.7362. Min Act: -0.1700
Data Index: 3341700 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.7049. Min Act: -0.1700
Data Index: 1534379 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.7049. Min Act: -0.1700
Data Index: 3783202 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.6737. Min Act: -0.1700
Data Index: 93529 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.7049. Min Act: -0.1700
Data Index: 4319386 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.6737. Min Act: -0.1700
Data Index: 2872679 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5799. Min Range: -7.5799
Max Act: 6.6737. Min Act: -0.1700
Data Index: 3625391 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19