Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.1742. Min Act: -0.1700
Data Index: 7958658 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.1585. Min Act: -0.1700
Data Index: 6075177 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.1427. Min Act: -0.1700
Data Index: 2029177 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.1112. Min Act: -0.1700
Data Index: 7467963 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.1112. Min Act: -0.1700
Data Index: 3021222 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0955. Min Act: -0.1700
Data Index: 353991 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0797. Min Act: -0.1700
Data Index: 4101571 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0639. Min Act: -0.1700
Data Index: 3563969 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0639. Min Act: -0.1700
Data Index: 3016139 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0481. Min Act: -0.1700
Data Index: 6204747 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0481. Min Act: -0.1700
Data Index: 2846856 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 4774121 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0324. Min Act: -0.1700
Data Index: 3705309 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0324. Min Act: -0.1700
Data Index: 4830152 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 2064392 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 6442813 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 4970285 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 6615839 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 2872637 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1742. Min Range: -3.1742
Max Act: 3.0166. Min Act: -0.1700
Data Index: 3729407 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19