Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3001 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.4133. Min Act: -0.1700
Data Index: 375040 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.4133. Min Act: -0.1700
Data Index: 3820037 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.4133. Min Act: -0.1700
Data Index: 2648609 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.4133. Min Act: -0.1700
Data Index: 8534234 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.3508. Min Act: -0.1700
Data Index: 4485857 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.4133. Min Act: -0.1700
Data Index: 6946917 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.2883. Min Act: -0.1700
Data Index: 8305653 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.2883. Min Act: -0.1700
Data Index: 2951256 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.2258. Min Act: -0.1700
Data Index: 2128715 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.2258. Min Act: -0.1700
Data Index: 1350950 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.2883. Min Act: -0.1700
Data Index: 4412926 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.2258. Min Act: -0.1700
Data Index: 1051613 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1633. Min Act: -0.1700
Data Index: 296349 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1633. Min Act: -0.1700
Data Index: 1226087 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1633. Min Act: -0.1700
Data Index: 6466663 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1633. Min Act: -0.1700
Data Index: 3593716 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1008. Min Act: -0.1700
Data Index: 1252234 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1008. Min Act: -0.1700
Data Index: 193776 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1008. Min Act: -0.1700
Data Index: 6197536 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4133. Min Range: -9.4133
Max Act: 9.1008. Min Act: -0.1700
Data Index: 6048552 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19