Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4426 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7972. Min Range: -6.7972
Max Act: 6.7972. Min Act: -0.1700
Data Index: 172700 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.9534. Min Act: -0.1700
Data Index: 4308995 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6468291 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.7659. Min Act: -0.1700
Data Index: 5813471 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.7034. Min Act: -0.1700
Data Index: 3884900 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.7034. Min Act: -0.1700
Data Index: 4714969 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.6409. Min Act: -0.1700
Data Index: 3587683 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3089958 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.6097. Min Act: -0.1700
Data Index: 1366313 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.6097. Min Act: -0.1700
Data Index: 1187430 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.5784. Min Act: -0.1700
Data Index: 2603571 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.5784. Min Act: -0.1700
Data Index: 764155 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.5784. Min Act: -0.1700
Data Index: 8311945 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.5472. Min Act: -0.1700
Data Index: 6557109 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.5472. Min Act: -0.1700
Data Index: 645753 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.4847. Min Act: -0.1700
Data Index: 2960320 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.4847. Min Act: -0.1700
Data Index: 1872982 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.4847. Min Act: -0.1700
Data Index: 2002940 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.4534. Min Act: -0.1700
Data Index: 7552918 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7972. Min Range: -6.7972
Max Act: 5.4534. Min Act: -0.1700
Data Index: 5164659 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19