Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.9680. Min Act: -0.1700
Data Index: 2792090 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.5930. Min Act: -0.1700
Data Index: 2502361 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.4680. Min Act: -0.1700
Data Index: 1170277 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.4680. Min Act: -0.1700
Data Index: 6848534 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.4055. Min Act: -0.1700
Data Index: 488599 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.4055. Min Act: -0.1700
Data Index: 7857544 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.4055. Min Act: -0.1700
Data Index: 8538717 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.3430. Min Act: -0.1700
Data Index: 5224451 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.2805. Min Act: -0.1700
Data Index: 176156 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 7185314 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 7972003 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 4149830 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 2184845 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.2180. Min Act: -0.1700
Data Index: 5150662 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.1555. Min Act: -0.1700
Data Index: 2056793 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9680. Min Range: -8.9680
Max Act: 8.0305. Min Act: -0.1700
Data Index: 100724 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9680. Min Range: -8.9680
Max Act: 7.9680. Min Act: -0.1700
Data Index: 1906172 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9680. Min Range: -8.9680
Max Act: 7.9680. Min Act: -0.1700
Data Index: 5186873 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9680. Min Range: -8.9680
Max Act: 7.9680. Min Act: -0.1700
Data Index: 3757790 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9680. Min Range: -8.9680
Max Act: 7.9680. Min Act: -0.1700
Data Index: 4762875 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19