Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3681 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.4963. Min Act: -0.1700
Data Index: 6826191 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.4338. Min Act: -0.1700
Data Index: 5991553 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.4338. Min Act: -0.1700
Data Index: 6383173 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.3713. Min Act: -0.1700
Data Index: 2284567 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.3713. Min Act: -0.1700
Data Index: 3101498 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.3088. Min Act: -0.1700
Data Index: 2388627 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 169973 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.3088. Min Act: -0.1700
Data Index: 803332 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.3088. Min Act: -0.1700
Data Index: 2843867 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.3088. Min Act: -0.1700
Data Index: 7093775 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 7234853 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 8252023 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 237084 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 2110154 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 777039 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2150. Min Act: -0.1700
Data Index: 554387 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2463. Min Act: -0.1700
Data Index: 433370 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2150. Min Act: -0.1700
Data Index: 7900647 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2150. Min Act: -0.1700
Data Index: 8107860 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4963. Min Range: -7.4963
Max Act: 7.2150. Min Act: -0.1700
Data Index: 1520952 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19