Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.4497. Min Range: -16.4497
Max Act: 16.4497. Min Act: -0.1700
Data Index: 8051619 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.4497. Min Range: -16.4497
Max Act: 16.3247. Min Act: -0.1700
Data Index: 7490883 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.4497. Min Range: -16.4497
Max Act: 15.4497. Min Act: -0.1700
Data Index: 2707580 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.4497. Min Range: -16.4497
Max Act: 15.2622. Min Act: -0.1700
Data Index: 2778930 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.4497. Min Range: -16.4497
Max Act: 15.0747. Min Act: -0.1700
Data Index: 5155579 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.5747. Min Act: -0.1700
Data Index: 3195875 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.5122. Min Act: -0.1700
Data Index: 2237409 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.3872. Min Act: -0.1700
Data Index: 6815241 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.4497. Min Act: -0.1700
Data Index: 8743990 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.3872. Min Act: -0.1700
Data Index: 4996730 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.3247. Min Act: -0.1700
Data Index: 10039 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.2622. Min Act: -0.1700
Data Index: 3804552 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.2622. Min Act: -0.1700
Data Index: 4180984 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.2622. Min Act: -0.1700
Data Index: 7948624 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.1997. Min Act: -0.1700
Data Index: 1316096 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.1997. Min Act: -0.1700
Data Index: 6176048 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.0747. Min Act: -0.1700
Data Index: 5540021 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.0122. Min Act: -0.1700
Data Index: 125561 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.0747. Min Act: -0.1700
Data Index: 2613486 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.4497. Min Range: -16.4497
Max Act: 14.0122. Min Act: -0.1700
Data Index: 4788546 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19