Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1065 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1237. Min Range: -5.1237
Max Act: 5.1237. Min Act: -0.1700
Data Index: 6436639 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.9987. Min Act: -0.1700
Data Index: 4671341 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.9362. Min Act: -0.1700
Data Index: 819810 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.9362. Min Act: -0.1700
Data Index: 5446389 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.9362. Min Act: -0.1700
Data Index: 2429768 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8737. Min Act: -0.1700
Data Index: 901821 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8112. Min Act: -0.1700
Data Index: 6408693 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8425. Min Act: -0.1700
Data Index: 4282089 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8425. Min Act: -0.1700
Data Index: 3910636 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8112. Min Act: -0.1700
Data Index: 8450377 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8112. Min Act: -0.1700
Data Index: 3404633 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.7800. Min Act: -0.1700
Data Index: 5948957 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.7800. Min Act: -0.1700
Data Index: 8316672 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.7800. Min Act: -0.1700
Data Index: 1555237 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.7800. Min Act: -0.1700
Data Index: 5123254 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.7487. Min Act: -0.1700
Data Index: 3509452 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8112. Min Act: -0.1700
Data Index: 4756758 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8112. Min Act: -0.1700
Data Index: 3862604 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.8112. Min Act: -0.1700
Data Index: 2324143 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1237. Min Range: -5.1237
Max Act: 4.7800. Min Act: -0.1700
Data Index: 5786514 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19