Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.3039. Min Act: -0.1700
Data Index: 2084 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.1476. Min Act: -0.1700
Data Index: 5609473 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.1476. Min Act: -0.1700
Data Index: 5951458 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0851. Min Act: -0.1700
Data Index: 7764328 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0539. Min Act: -0.1700
Data Index: 8106697 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0851. Min Act: -0.1700
Data Index: 4025111 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0851. Min Act: -0.1700
Data Index: 2797898 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0851. Min Act: -0.1694
Data Index: 5163412 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0539. Min Act: -0.1700
Data Index: 5728910 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0851. Min Act: -0.1700
Data Index: 3836585 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0226. Min Act: -0.1700
Data Index: 8325020 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3039. Min Range: -6.3039
Max Act: 5.9914. Min Act: -0.1700
Data Index: 5635383 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0226. Min Act: -0.1700
Data Index: 2917542 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3039. Min Range: -6.3039
Max Act: 5.9914. Min Act: -0.1700
Data Index: 970471 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0226. Min Act: -0.1697
Data Index: 3164387 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3039. Min Range: -6.3039
Max Act: 5.9914. Min Act: -0.1700
Data Index: 1825324 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0226. Min Act: -0.1700
Data Index: 7922614 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3039. Min Range: -6.3039
Max Act: 6.0226. Min Act: -0.1699
Data Index: 6056599 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3039. Min Range: -6.3039
Max Act: 5.9914. Min Act: -0.1699
Data Index: 4598857 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3039. Min Range: -6.3039
Max Act: 5.9914. Min Act: -0.1700
Data Index: 2310052 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19