Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0168. Min Range: -6.0168
Max Act: 6.0168. Min Act: -0.1700
Data Index: 3291270 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.8918. Min Act: -0.1700
Data Index: 264272 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.8918. Min Act: -0.1700
Data Index: 157533 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.8606. Min Act: -0.1700
Data Index: 7908711 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.8606. Min Act: -0.1700
Data Index: 5429300 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7981. Min Act: -0.1700
Data Index: 7506542 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7981. Min Act: -0.1700
Data Index: 5900437 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.8293. Min Act: -0.1700
Data Index: 5472212 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.8293. Min Act: -0.1700
Data Index: 4572705 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7981. Min Act: -0.1700
Data Index: 2338554 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7668. Min Act: -0.1700
Data Index: 3648140 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7668. Min Act: -0.1700
Data Index: 298304 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7981. Min Act: -0.1700
Data Index: 1111497 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7668. Min Act: -0.1700
Data Index: 8261335 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7356. Min Act: -0.1700
Data Index: 5392239 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7356. Min Act: -0.1700
Data Index: 6789 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7356. Min Act: -0.1700
Data Index: 5393151 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7043. Min Act: -0.1700
Data Index: 6691236 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7043. Min Act: -0.1700
Data Index: 5496322 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0168. Min Range: -6.0168
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2655445 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19