Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.8543. Min Act: -0.1700
Data Index: 8581476 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.7918. Min Act: -0.1700
Data Index: 2238873 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.7293. Min Act: -0.1700
Data Index: 6735137 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6043. Min Act: -0.1700
Data Index: 6617427 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6043. Min Act: -0.1700
Data Index: 8272713 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6668. Min Act: -0.1700
Data Index: 249307 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6668. Min Act: -0.1700
Data Index: 6470597 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.5418. Min Act: -0.1700
Data Index: 4587446 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6668. Min Act: -0.1700
Data Index: 1864857 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6043. Min Act: -0.1700
Data Index: 8553841 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6043. Min Act: -0.1700
Data Index: 5351411 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.5418. Min Act: -0.1700
Data Index: 4035672 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.5418. Min Act: -0.1700
Data Index: 4232207 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.5418. Min Act: -0.1700
Data Index: 3781589 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.4168. Min Act: -0.1700
Data Index: 8714585 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.5418. Min Act: -0.1700
Data Index: 977524 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.6043. Min Act: -0.1700
Data Index: 4856212 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.4168. Min Act: -0.1700
Data Index: 6357160 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.4793. Min Act: -0.1700
Data Index: 6403946 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8543. Min Range: -8.8543
Max Act: 8.4168. Min Act: -0.1700
Data Index: 2591628 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19