Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3965. Min Range: -5.3965
Max Act: 5.3965. Min Act: -0.1700
Data Index: 8420714 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3965. Min Range: -5.3965
Max Act: 5.1777. Min Act: -0.1700
Data Index: 1870296 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3965. Min Range: -5.3965
Max Act: 5.1777. Min Act: -0.1700
Data Index: 8030095 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.9902. Min Act: -0.1700
Data Index: 5146473 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.9902. Min Act: -0.1700
Data Index: 2390303 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.9902. Min Act: -0.1700
Data Index: 6683579 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.9277. Min Act: -0.1700
Data Index: 6689268 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.9277. Min Act: -0.1700
Data Index: 2550485 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8965. Min Act: -0.1700
Data Index: 5528479 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8652. Min Act: -0.1700
Data Index: 627860 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8340. Min Act: -0.1700
Data Index: 352518 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8027. Min Act: -0.1700
Data Index: 7594640 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8340. Min Act: -0.1700
Data Index: 4790189 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.7715. Min Act: -0.1700
Data Index: 7963178 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8340. Min Act: -0.1700
Data Index: 29909 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5039706 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.7715. Min Act: -0.1700
Data Index: 3455802 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.7715. Min Act: -0.1700
Data Index: 1441243 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.7715. Min Act: -0.1700
Data Index: 3931084 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3965. Min Range: -5.3965
Max Act: 4.7715. Min Act: -0.1700
Data Index: 1713096 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19