Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3308. Min Range: -8.3308
Max Act: 8.3308. Min Act: -0.1700
Data Index: 4387075 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3308. Min Range: -8.3308
Max Act: 8.0808. Min Act: -0.1700
Data Index: 6652779 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.8933. Min Act: -0.1700
Data Index: 6600316 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.8308. Min Act: -0.1700
Data Index: 5754694 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.7371. Min Act: -0.1700
Data Index: 6177065 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.7058. Min Act: -0.1700
Data Index: 7343541 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.6433. Min Act: -0.1700
Data Index: 8805233 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.4871. Min Act: -0.1700
Data Index: 4460410 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.4871. Min Act: -0.1700
Data Index: 8722114 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.4871. Min Act: -0.1700
Data Index: 5198334 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.4246. Min Act: -0.1700
Data Index: 2233503 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.4558. Min Act: -0.1700
Data Index: 8781705 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3621. Min Act: -0.1700
Data Index: 3069955 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3621. Min Act: -0.1700
Data Index: 3398617 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3308. Min Act: -0.1700
Data Index: 6898264 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3621. Min Act: -0.1700
Data Index: 1987449 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.4246. Min Act: -0.1700
Data Index: 5836364 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3621. Min Act: -0.1700
Data Index: 5031684 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3308. Min Act: -0.1700
Data Index: 3076332 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3308. Min Range: -8.3308
Max Act: 7.3308. Min Act: -0.1700
Data Index: 6372297 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19