Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.2528. Min Act: -0.1700
Data Index: 1314886 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.2215. Min Act: -0.1700
Data Index: 8442050 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.1590. Min Act: -0.1700
Data Index: 7310048 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.1278. Min Act: -0.1700
Data Index: 1257819 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.0653. Min Act: -0.1700
Data Index: 6620240 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.0653. Min Act: -0.1700
Data Index: 6088439 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.0653. Min Act: -0.1700
Data Index: 1275981 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.0340. Min Act: -0.1700
Data Index: 3606252 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.0028. Min Act: -0.1700
Data Index: 6750086 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2528. Min Range: -5.2528
Max Act: 5.0028. Min Act: -0.1700
Data Index: 915330 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.9403. Min Act: -0.1700
Data Index: 4889578 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.9090. Min Act: -0.1700
Data Index: 2313618 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7786673 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8778. Min Act: -0.1700
Data Index: 4641033 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8465. Min Act: -0.1700
Data Index: 6502906 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8778. Min Act: -0.1700
Data Index: 6620243 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8778. Min Act: -0.1700
Data Index: 1657639 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8153. Min Act: -0.1700
Data Index: 7640475 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8465. Min Act: -0.1700
Data Index: 3950068 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2528. Min Range: -5.2528
Max Act: 4.8465. Min Act: -0.1700
Data Index: 5223070 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19