Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.8682. Min Act: -0.1700
Data Index: 4352985 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.6182. Min Act: -0.1700
Data Index: 7660912 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.5557. Min Act: -0.1700
Data Index: 2504768 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.4932. Min Act: -0.1700
Data Index: 3694138 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.4307. Min Act: -0.1700
Data Index: 5744293 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.3057. Min Act: -0.1700
Data Index: 4755960 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.3057. Min Act: -0.1700
Data Index: 1846696 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.2432. Min Act: -0.1700
Data Index: 8501887 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.1182. Min Act: -0.1700
Data Index: 7363884 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.1182. Min Act: -0.1700
Data Index: 1833457 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.0557. Min Act: -0.1700
Data Index: 86433 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8682. Min Range: -11.8682
Max Act: 10.9932. Min Act: -0.1700
Data Index: 2646424 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.0557. Min Act: -0.1700
Data Index: 5413951 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.0557. Min Act: -0.1700
Data Index: 3558279 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8682. Min Range: -11.8682
Max Act: 11.0557. Min Act: -0.1700
Data Index: 4608415 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8682. Min Range: -11.8682
Max Act: 10.9932. Min Act: -0.1700
Data Index: 1124879 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8682. Min Range: -11.8682
Max Act: 10.8682. Min Act: -0.1700
Data Index: 5693342 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8682. Min Range: -11.8682
Max Act: 10.9307. Min Act: -0.1700
Data Index: 2553173 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8682. Min Range: -11.8682
Max Act: 10.9307. Min Act: -0.1700
Data Index: 2614027 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8682. Min Range: -11.8682
Max Act: 10.9307. Min Act: -0.1700
Data Index: 1775623 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19