Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.6593. Min Act: -0.1700
Data Index: 2737706 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.6280. Min Act: -0.1700
Data Index: 246558 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.5343. Min Act: -0.1700
Data Index: 1808271 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.4093. Min Act: -0.1700
Data Index: 4845757 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.4405. Min Act: -0.1700
Data Index: 903121 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.4405. Min Act: -0.1700
Data Index: 1785482 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.4093. Min Act: -0.1700
Data Index: 5907534 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.4093. Min Act: -0.1700
Data Index: 7083915 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.3468. Min Act: -0.1700
Data Index: 817276 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.3155. Min Act: -0.1700
Data Index: 2446208 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.3155. Min Act: -0.1700
Data Index: 1604898 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.3155. Min Act: -0.1700
Data Index: 1338997 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.3155. Min Act: -0.1700
Data Index: 436339 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.2843. Min Act: -0.1700
Data Index: 3567772 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.3155. Min Act: -0.1700
Data Index: 4142222 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.2530. Min Act: -0.1700
Data Index: 1959449 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.2218. Min Act: -0.1700
Data Index: 4137389 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.2530. Min Act: -0.1700
Data Index: 101915 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.2530. Min Act: -0.1700
Data Index: 6860612 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6593. Min Range: -6.6593
Max Act: 6.2530. Min Act: -0.1700
Data Index: 2884168 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19