Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.8202. Min Act: -0.1700
Data Index: 7066210 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.6327. Min Act: -0.1700
Data Index: 3888016 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.5389. Min Act: -0.1700
Data Index: 8393782 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.4764. Min Act: -0.1700
Data Index: 3433885 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.4452. Min Act: -0.1700
Data Index: 2444320 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.3827. Min Act: -0.1700
Data Index: 4298046 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.3827. Min Act: -0.1700
Data Index: 1194681 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.3514. Min Act: -0.1700
Data Index: 4606935 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.3514. Min Act: -0.1700
Data Index: 324988 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.3202. Min Act: -0.1700
Data Index: 1606748 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2889. Min Act: -0.1700
Data Index: 690463 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2889. Min Act: -0.1700
Data Index: 2754993 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2889. Min Act: -0.1700
Data Index: 8678315 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2889. Min Act: -0.1700
Data Index: 1129500 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2889. Min Act: -0.1700
Data Index: 3344787 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2577. Min Act: -0.1700
Data Index: 3881259 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2577. Min Act: -0.1700
Data Index: 7094921 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2577. Min Act: -0.1700
Data Index: 7589906 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2577. Min Act: -0.1700
Data Index: 5289199 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8202. Min Range: -4.8202
Max Act: 4.2577. Min Act: -0.1700
Data Index: 6785835 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19