Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0069. Min Range: -9.0069
Max Act: 9.0069. Min Act: -0.1700
Data Index: 8077938 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.5069. Min Act: -0.1700
Data Index: 6022994 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.4444. Min Act: -0.1700
Data Index: 3945941 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.3819. Min Act: -0.1700
Data Index: 397628 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.3194. Min Act: -0.1700
Data Index: 4802955 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.3194. Min Act: -0.1700
Data Index: 1741857 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.3194. Min Act: -0.1700
Data Index: 2184398 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.3194. Min Act: -0.1700
Data Index: 3012656 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.2569. Min Act: -0.1700
Data Index: 1990534 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1944. Min Act: -0.1700
Data Index: 1425065 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1944. Min Act: -0.1700
Data Index: 3191411 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1944. Min Act: -0.1700
Data Index: 1417509 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1319. Min Act: -0.1700
Data Index: 2108932 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1319. Min Act: -0.1700
Data Index: 8727490 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1319. Min Act: -0.1700
Data Index: 5251010 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.1319. Min Act: -0.1700
Data Index: 5388081 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.0694. Min Act: -0.1700
Data Index: 20520 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.0694. Min Act: -0.1700
Data Index: 857701 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.0694. Min Act: -0.1700
Data Index: 3627562 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0069. Min Range: -9.0069
Max Act: 8.0694. Min Act: -0.1700
Data Index: 7186828 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19