Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3450. Min Range: -6.3450
Max Act: 6.3450. Min Act: -0.1700
Data Index: 1631424 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3450. Min Range: -6.3450
Max Act: 6.3137. Min Act: -0.1700
Data Index: 5042846 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3450. Min Range: -6.3450
Max Act: 6.2512. Min Act: -0.1700
Data Index: 5042847 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3450. Min Range: -6.3450
Max Act: 6.2200. Min Act: -0.1700
Data Index: 8621658 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.9700. Min Act: -0.1700
Data Index: 3673938 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.8762. Min Act: -0.1700
Data Index: 3833587 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.8450. Min Act: -0.1700
Data Index: 8017162 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.8137. Min Act: -0.1700
Data Index: 6031348 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.8137. Min Act: -0.1700
Data Index: 5148468 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.8137. Min Act: -0.1700
Data Index: 42195 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7825. Min Act: -0.1700
Data Index: 6440775 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7512. Min Act: -0.1700
Data Index: 5420603 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7825. Min Act: -0.1700
Data Index: 7653797 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7512. Min Act: -0.1700
Data Index: 5731350 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7512. Min Act: -0.1700
Data Index: 4389050 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7200. Min Act: -0.1700
Data Index: 3479716 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7200. Min Act: -0.1700
Data Index: 5577263 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7200. Min Act: -0.1700
Data Index: 4955857 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7200. Min Act: -0.1700
Data Index: 872585 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3450. Min Range: -6.3450
Max Act: 5.7200. Min Act: -0.1700
Data Index: 8493347 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19