Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 214 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1981. Min Range: -6.1981
Max Act: 6.1981. Min Act: -0.1700
Data Index: 8540568 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1981. Min Range: -6.1981
Max Act: 6.1356. Min Act: -0.1700
Data Index: 7883087 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.9794. Min Act: -0.1700
Data Index: 1859247 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.9794. Min Act: -0.1700
Data Index: 1160528 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.9169. Min Act: -0.1700
Data Index: 2214135 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.9481. Min Act: -0.1700
Data Index: 4945269 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.8544. Min Act: -0.1700
Data Index: 6885688 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.8231. Min Act: -0.1700
Data Index: 6123264 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.7606. Min Act: -0.1700
Data Index: 1206946 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.7294. Min Act: -0.1700
Data Index: 893705 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.7294. Min Act: -0.1700
Data Index: 3812111 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.7294. Min Act: -0.1700
Data Index: 666867 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6981. Min Act: -0.1700
Data Index: 2744432 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6981. Min Act: -0.1700
Data Index: 5631824 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6981. Min Act: -0.1700
Data Index: 2328964 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6669. Min Act: -0.1700
Data Index: 5335625 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6669. Min Act: -0.1700
Data Index: 7502890 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6356. Min Act: -0.1700
Data Index: 1000299 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6356. Min Act: -0.1700
Data Index: 3970396 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1981. Min Range: -6.1981
Max Act: 5.6356. Min Act: -0.1700
Data Index: 805907 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19