Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 376 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.4463. Min Act: -0.1700
Data Index: 3959048 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.2588. Min Act: -0.1700
Data Index: 7393172 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.2276. Min Act: -0.1700
Data Index: 1443530 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.2276. Min Act: -0.1700
Data Index: 5374710 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.1963. Min Act: -0.1700
Data Index: 8169069 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.1651. Min Act: -0.1700
Data Index: 3798825 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.1338. Min Act: -0.1700
Data Index: 1490809 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.1026. Min Act: -0.1700
Data Index: 261175 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.1338. Min Act: -0.1700
Data Index: 4305495 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0713. Min Act: -0.1700
Data Index: 8791554 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0713. Min Act: -0.1700
Data Index: 405 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0713. Min Act: -0.1700
Data Index: 435625 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0401. Min Act: -0.1700
Data Index: 3739412 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0401. Min Act: -0.1700
Data Index: 1108883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0401. Min Act: -0.1700
Data Index: 4305494 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0401. Min Act: -0.1700
Data Index: 2542909 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0088. Min Act: -0.1700
Data Index: 797930 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4463. Min Range: -5.4463
Max Act: 5.0088. Min Act: -0.1700
Data Index: 5711938 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4463. Min Range: -5.4463
Max Act: 4.9776. Min Act: -0.1700
Data Index: 5988466 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4463. Min Range: -5.4463
Max Act: 4.9776. Min Act: -0.1700
Data Index: 6727718 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19