Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5307 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1970. Min Range: -5.1970
Max Act: 5.1970. Min Act: -0.1700
Data Index: 4477179 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1970. Min Range: -5.1970
Max Act: 5.1345. Min Act: -0.1700
Data Index: 7367068 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1970. Min Range: -5.1970
Max Act: 5.0408. Min Act: -0.1700
Data Index: 6961623 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1970. Min Range: -5.1970
Max Act: 5.0095. Min Act: -0.1700
Data Index: 3748734 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1970. Min Range: -5.1970
Max Act: 5.0408. Min Act: -0.1700
Data Index: 1700637 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1970. Min Range: -5.1970
Max Act: 5.0095. Min Act: -0.1700
Data Index: 6083987 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.9470. Min Act: -0.1700
Data Index: 8295215 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.8533. Min Act: -0.1700
Data Index: 1190840 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.8220. Min Act: -0.1700
Data Index: 6482269 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7908. Min Act: -0.1700
Data Index: 7870063 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7908. Min Act: -0.1700
Data Index: 2549463 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7908. Min Act: -0.1700
Data Index: 674976 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7908. Min Act: -0.1700
Data Index: 8692506 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7908. Min Act: -0.1700
Data Index: 6127054 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7908. Min Act: -0.1700
Data Index: 6625779 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7595. Min Act: -0.1700
Data Index: 5945978 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7595. Min Act: -0.1700
Data Index: 8645110 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7595. Min Act: -0.1700
Data Index: 5678633 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7595. Min Act: -0.1700
Data Index: 1695097 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1970. Min Range: -5.1970
Max Act: 4.7283. Min Act: -0.1700
Data Index: 7223006 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19