Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.2706. Min Act: -0.1700
Data Index: 6975222 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.1143. Min Act: -0.1700
Data Index: 6019712 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.0518. Min Act: -0.1700
Data Index: 2134146 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.0206. Min Act: -0.1700
Data Index: 1277735 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9893. Min Act: -0.1700
Data Index: 2852930 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9893. Min Act: -0.1700
Data Index: 7344718 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9581. Min Act: -0.1700
Data Index: 2118210 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 347104 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8643. Min Act: -0.1700
Data Index: 7718078 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8643. Min Act: -0.1700
Data Index: 2961248 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8643. Min Act: -0.1700
Data Index: 7145411 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8018. Min Act: -0.1700
Data Index: 7789337 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8331. Min Act: -0.1700
Data Index: 392393 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8018. Min Act: -0.1700
Data Index: 3669534 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.7706. Min Act: -0.1700
Data Index: 2214308 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.7706. Min Act: -0.1700
Data Index: 982384 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8018. Min Act: -0.1700
Data Index: 2961245 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.7706. Min Act: -0.1700
Data Index: 6015238 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.7393. Min Act: -0.1700
Data Index: 4221794 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.7706. Min Act: -0.1700
Data Index: 1530644 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19