Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1888. Min Range: -5.1888
Max Act: 5.1888. Min Act: -0.1700
Data Index: 1896669 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1888. Min Range: -5.1888
Max Act: 5.1575. Min Act: -0.1700
Data Index: 4194331 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1888. Min Range: -5.1888
Max Act: 5.1888. Min Act: -0.1700
Data Index: 880475 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1888. Min Range: -5.1888
Max Act: 5.0638. Min Act: -0.1700
Data Index: 2081911 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.9388. Min Act: -0.1700
Data Index: 7714430 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.9075. Min Act: -0.1700
Data Index: 7926962 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.9388. Min Act: -0.1700
Data Index: 7947537 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.9075. Min Act: -0.1700
Data Index: 2192497 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.9075. Min Act: -0.1700
Data Index: 617019 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.9075. Min Act: -0.1700
Data Index: 6383579 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8450. Min Act: -0.1700
Data Index: 5043791 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8763. Min Act: -0.1700
Data Index: 3435536 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8763. Min Act: -0.1700
Data Index: 6326047 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8763. Min Act: -0.1700
Data Index: 8739144 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8450. Min Act: -0.1700
Data Index: 3759536 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8450. Min Act: -0.1700
Data Index: 395329 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8763. Min Act: -0.1700
Data Index: 4874645 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8450. Min Act: -0.1700
Data Index: 6049502 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8450. Min Act: -0.1700
Data Index: 2241803 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1888. Min Range: -5.1888
Max Act: 4.8763. Min Act: -0.1700
Data Index: 6869283 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19