Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.7461. Min Act: -0.1700
Data Index: 946685 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.8086. Min Act: -0.1700
Data Index: 5565310 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.6836. Min Act: -0.1700
Data Index: 874229 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.5586. Min Act: -0.1700
Data Index: 8564165 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.4961. Min Act: -0.1700
Data Index: 3371737 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.4961. Min Act: -0.1700
Data Index: 6913856 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.4336. Min Act: -0.1700
Data Index: 5187128 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.3711. Min Act: -0.1700
Data Index: 6900489 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.2461. Min Act: -0.1700
Data Index: 3371993 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.2461. Min Act: -0.1700
Data Index: 1979233 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.2461. Min Act: -0.1700
Data Index: 8668137 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.1836. Min Act: -0.1700
Data Index: 2879645 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.1211. Min Act: -0.1700
Data Index: 7742409 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.1211. Min Act: -0.1700
Data Index: 4038385 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.0586. Min Act: -0.1700
Data Index: 6955866 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8086. Min Range: -9.8086
Max Act: 9.1211. Min Act: -0.1700
Data Index: 5518041 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8086. Min Range: -9.8086
Max Act: 8.9961. Min Act: -0.1700
Data Index: 7931257 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8086. Min Range: -9.8086
Max Act: 8.9336. Min Act: -0.1700
Data Index: 2404199 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8086. Min Range: -9.8086
Max Act: 8.9961. Min Act: -0.1700
Data Index: 2559391 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8086. Min Range: -9.8086
Max Act: 8.8711. Min Act: -0.1700
Data Index: 8346501 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19