Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3718 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4552. Min Range: -6.4552
Max Act: 6.4552. Min Act: -0.1700
Data Index: 8122214 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4552. Min Range: -6.4552
Max Act: 6.2365. Min Act: -0.1700
Data Index: 7571641 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4552. Min Range: -6.4552
Max Act: 6.1115. Min Act: -0.1700
Data Index: 1577853 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4552. Min Range: -6.4552
Max Act: 6.1115. Min Act: -0.1700
Data Index: 4747751 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4552. Min Range: -6.4552
Max Act: 6.0490. Min Act: -0.1700
Data Index: 5947147 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.9552. Min Act: -0.1700
Data Index: 7159024 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8927. Min Act: -0.1700
Data Index: 5996672 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8615. Min Act: -0.1700
Data Index: 6732300 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8927. Min Act: -0.1700
Data Index: 4399111 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8615. Min Act: -0.1700
Data Index: 1084400 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8615. Min Act: -0.1700
Data Index: 1912974 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2327080 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8615. Min Act: -0.1700
Data Index: 4546586 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8302. Min Act: -0.1700
Data Index: 2653716 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8302. Min Act: -0.1700
Data Index: 5288194 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.8302. Min Act: -0.1700
Data Index: 7839122 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.7990. Min Act: -0.1700
Data Index: 2726350 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.7990. Min Act: -0.1700
Data Index: 2223179 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.7990. Min Act: -0.1700
Data Index: 3728033 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4552. Min Range: -6.4552
Max Act: 5.7677. Min Act: -0.1700
Data Index: 197190 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19