Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5830 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.7744. Min Act: -0.1700
Data Index: 5749131 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.7119. Min Act: -0.1700
Data Index: 4113517 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.6494. Min Act: -0.1700
Data Index: 7403757 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.5869. Min Act: -0.1700
Data Index: 2818316 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.5869. Min Act: -0.1700
Data Index: 6387113 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.5869. Min Act: -0.1700
Data Index: 7201472 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.5557. Min Act: -0.1700
Data Index: 5348460 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.5557. Min Act: -0.1700
Data Index: 3205788 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.5244. Min Act: -0.1700
Data Index: 3408565 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.4932. Min Act: -0.1700
Data Index: 1282630 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.4932. Min Act: -0.1700
Data Index: 923822 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.4619. Min Act: -0.1700
Data Index: 1147250 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.4619. Min Act: -0.1700
Data Index: 1556149 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.4307. Min Act: -0.1700
Data Index: 1319799 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.4307. Min Act: -0.1700
Data Index: 8708366 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.3994. Min Act: -0.1700
Data Index: 2330317 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.3994. Min Act: -0.1700
Data Index: 4630992 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.3994. Min Act: -0.1700
Data Index: 7971198 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.3682. Min Act: -0.1700
Data Index: 419371 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7744. Min Range: -7.7744
Max Act: 7.3369. Min Act: -0.1700
Data Index: 3513414 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19