Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4838 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.4775. Min Act: -0.1700
Data Index: 7561147 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.3838. Min Act: -0.1700
Data Index: 306223 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.3213. Min Act: -0.1700
Data Index: 4446372 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.2900. Min Act: -0.1700
Data Index: 8609973 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.2588. Min Act: -0.1700
Data Index: 4898849 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.2275. Min Act: -0.1700
Data Index: 7489717 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.1963. Min Act: -0.1700
Data Index: 338348 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.1650. Min Act: -0.1700
Data Index: 5894394 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.1963. Min Act: -0.1700
Data Index: 142623 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.1963. Min Act: -0.1700
Data Index: 4972900 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.1338. Min Act: -0.1700
Data Index: 1376650 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.1025. Min Act: -0.1700
Data Index: 3899788 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.0088. Min Act: -0.1700
Data Index: 6734889 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.0088. Min Act: -0.1700
Data Index: 6041073 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.0088. Min Act: -0.1700
Data Index: 7277926 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.0088. Min Act: -0.1700
Data Index: 2335059 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.0088. Min Act: -0.1700
Data Index: 2717089 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4775. Min Range: -7.4775
Max Act: 7.0088. Min Act: -0.1700
Data Index: 4932815 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4775. Min Range: -7.4775
Max Act: 6.9463. Min Act: -0.1700
Data Index: 6292028 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4775. Min Range: -7.4775
Max Act: 6.9775. Min Act: -0.1700
Data Index: 2522281 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19