Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1309 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2568. Min Range: -8.2568
Max Act: 8.2568. Min Act: -0.1700
Data Index: 3242105 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2568. Min Range: -8.2568
Max Act: 8.0693. Min Act: -0.1700
Data Index: 4162887 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2568. Min Range: -8.2568
Max Act: 8.0068. Min Act: -0.1700
Data Index: 7890465 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.8818. Min Act: -0.1700
Data Index: 1131715 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.8818. Min Act: -0.1700
Data Index: 2800213 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.8193. Min Act: -0.1700
Data Index: 7994560 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.8193. Min Act: -0.1700
Data Index: 1136559 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.7568. Min Act: -0.1700
Data Index: 6921142 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.6943. Min Act: -0.1700
Data Index: 6742460 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.6943. Min Act: -0.1700
Data Index: 1789654 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.6943. Min Act: -0.1700
Data Index: 7730724 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.6318. Min Act: -0.1700
Data Index: 1652129 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.6318. Min Act: -0.1700
Data Index: 1911037 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.6005. Min Act: -0.1700
Data Index: 3833426 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.5693. Min Act: -0.1700
Data Index: 7499035 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.5693. Min Act: -0.1700
Data Index: 5720056 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.5068. Min Act: -0.1700
Data Index: 1417854 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.5068. Min Act: -0.1700
Data Index: 1360775 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.5380. Min Act: -0.1700
Data Index: 7785574 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2568. Min Range: -8.2568
Max Act: 7.4443. Min Act: -0.1700
Data Index: 2994766 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19