Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.2246. Min Act: -0.1538
Data Index: 4940353 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.2559. Min Act: -0.1693
Data Index: 7488071 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.1934. Min Act: -0.1606
Data Index: 3280013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.1309. Min Act: -0.1679
Data Index: 6433957 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.1309. Min Act: -0.1694
Data Index: 799387 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0683. Min Act: -0.1641
Data Index: 2882680 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0683. Min Act: -0.1693
Data Index: 8537970 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0371. Min Act: -0.1699
Data Index: 5629767 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0058. Min Act: -0.1658
Data Index: 4122512 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0371. Min Act: -0.1639
Data Index: 2054387 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0683. Min Act: -0.1577
Data Index: 8330408 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2559. Min Range: -4.2559
Max Act: 4.0058. Min Act: -0.1691
Data Index: 4619125 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9433. Min Act: -0.1636
Data Index: 6960149 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9433. Min Act: -0.1700
Data Index: 7467273 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9746. Min Act: -0.1586
Data Index: 4707608 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9746. Min Act: -0.1654
Data Index: 2055256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9746. Min Act: -0.1641
Data Index: 6602349 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9433. Min Act: -0.1698
Data Index: 4689855 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9746. Min Act: -0.1486
Data Index: 337384 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2559. Min Range: -4.2559
Max Act: 3.9746. Min Act: -0.1686
Data Index: 1255313 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19