Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.5748. Min Act: -0.1700
Data Index: 2780828 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4871. Min Act: -0.1700
Data Index: 5508676 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4695. Min Act: -0.1700
Data Index: 5464092 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4344. Min Act: -0.1690
Data Index: 5526079 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3815. Min Act: -0.1700
Data Index: 828755 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3991. Min Act: -0.1700
Data Index: 4464923 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3639. Min Act: -0.1699
Data Index: 5291756 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3639. Min Act: -0.1700
Data Index: 1751245 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3462. Min Act: -0.1699
Data Index: 131794 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3462. Min Act: -0.1673
Data Index: 4173184 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3462. Min Act: -0.1649
Data Index: 554885 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3462. Min Act: -0.1700
Data Index: 8510950 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3286. Min Act: -0.1700
Data Index: 3694484 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3110. Min Act: -0.1700
Data Index: 94675 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3110. Min Act: -0.1700
Data Index: 7655026 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3110. Min Act: -0.1688
Data Index: 5240747 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3110. Min Act: -0.1700
Data Index: 508888 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2933. Min Act: -0.1700
Data Index: 3782770 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2933. Min Act: -0.1677
Data Index: 4856463 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2933. Min Act: -0.1699
Data Index: 890974 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19