Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.3478. Min Act: -0.1700
Data Index: 1592963 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.2228. Min Act: -0.1700
Data Index: 8348652 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.2228. Min Act: -0.1700
Data Index: 5759503 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.2540. Min Act: -0.1700
Data Index: 5755053 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.2228. Min Act: -0.1700
Data Index: 2073397 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.1915. Min Act: -0.1700
Data Index: 4805416 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.1915. Min Act: -0.1700
Data Index: 3023979 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.1603. Min Act: -0.1700
Data Index: 2439360 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4244263 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.1290. Min Act: -0.1700
Data Index: 850154 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0978. Min Act: -0.1700
Data Index: 8740942 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0978. Min Act: -0.1700
Data Index: 7091628 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0978. Min Act: -0.1700
Data Index: 8047362 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0353. Min Act: -0.1700
Data Index: 5777817 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0665. Min Act: -0.1700
Data Index: 3499347 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0665. Min Act: -0.1700
Data Index: 6292226 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0665. Min Act: -0.1700
Data Index: 4843919 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0353. Min Act: -0.1700
Data Index: 870725 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0353. Min Act: -0.1700
Data Index: 6806601 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3478. Min Range: -5.3478
Max Act: 5.0665. Min Act: -0.1700
Data Index: 3269999 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19