Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5675 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.4787. Min Act: -0.1700
Data Index: 5403226 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.4162. Min Act: -0.1700
Data Index: 1799216 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.3850. Min Act: -0.1700
Data Index: 638708 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.3850. Min Act: -0.1700
Data Index: 2528709 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.3537. Min Act: -0.1700
Data Index: 7435254 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.3537. Min Act: -0.1700
Data Index: 6503449 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.3225. Min Act: -0.1700
Data Index: 8371055 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2912. Min Act: -0.1700
Data Index: 757936 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2912. Min Act: -0.1700
Data Index: 5455492 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2912. Min Act: -0.1700
Data Index: 965846 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2912. Min Act: -0.1700
Data Index: 1256276 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2912. Min Act: -0.1700
Data Index: 7632538 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2600. Min Act: -0.1700
Data Index: 6688903 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2287. Min Act: -0.1700
Data Index: 1507370 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2287. Min Act: -0.1700
Data Index: 2759084 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2600. Min Act: -0.1700
Data Index: 2632226 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.2287. Min Act: -0.1700
Data Index: 5123442 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.1975. Min Act: -0.1700
Data Index: 100792 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.1662. Min Act: -0.1700
Data Index: 7344146 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4787. Min Range: -5.4787
Max Act: 5.1662. Min Act: -0.1700
Data Index: 1377179 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19