Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.4086. Min Act: -0.1700
Data Index: 5704570 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.3461. Min Act: -0.1700
Data Index: 5538694 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.3149. Min Act: -0.1700
Data Index: 5844527 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.2836. Min Act: -0.1700
Data Index: 11369 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.2211. Min Act: -0.1700
Data Index: 8019149 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1899. Min Act: -0.1700
Data Index: 3064789 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1586. Min Act: -0.1700
Data Index: 1462060 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1899. Min Act: -0.1700
Data Index: 356383 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1274. Min Act: -0.1700
Data Index: 632308 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1274. Min Act: -0.1700
Data Index: 3496369 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1586. Min Act: -0.1700
Data Index: 4324517 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0961. Min Act: -0.1700
Data Index: 7298410 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.1274. Min Act: -0.1700
Data Index: 6109193 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0961. Min Act: -0.1700
Data Index: 7308169 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0649. Min Act: -0.1700
Data Index: 4218196 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0961. Min Act: -0.1700
Data Index: 8071476 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0336. Min Act: -0.1700
Data Index: 2418992 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0649. Min Act: -0.1700
Data Index: 1157766 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0649. Min Act: -0.1700
Data Index: 2026662 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4086. Min Range: -7.4086
Max Act: 7.0649. Min Act: -0.1700
Data Index: 395424 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19