Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4702 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.8442. Min Act: -0.1700
Data Index: 373999 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.7817. Min Act: -0.1700
Data Index: 281976 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.7192. Min Act: -0.1700
Data Index: 6453637 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.7192. Min Act: -0.1700
Data Index: 4073084 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.6567. Min Act: -0.1700
Data Index: 5972954 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.7192. Min Act: -0.1700
Data Index: 6453636 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.6567. Min Act: -0.1700
Data Index: 7535132 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.6254. Min Act: -0.1700
Data Index: 2311556 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.6254. Min Act: -0.1700
Data Index: 8387660 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.5942. Min Act: -0.1700
Data Index: 6269878 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.5317. Min Act: -0.1700
Data Index: 8667584 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.5317. Min Act: -0.1700
Data Index: 5188084 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.5317. Min Act: -0.1700
Data Index: 5725238 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.5317. Min Act: -0.1700
Data Index: 2703864 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.4379. Min Act: -0.1700
Data Index: 7769987 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.4379. Min Act: -0.1700
Data Index: 312037 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.4067. Min Act: -0.1700
Data Index: 6286261 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.4067. Min Act: -0.1700
Data Index: 5470078 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.3754. Min Act: -0.1700
Data Index: 2494877 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8442. Min Range: -7.8442
Max Act: 7.3754. Min Act: -0.1700
Data Index: 4459388 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19