Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.2184. Min Act: -0.1700
Data Index: 1094659 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0934. Min Act: -0.1700
Data Index: 5295991 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.1247. Min Act: -0.1700
Data Index: 6001576 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0934. Min Act: -0.1700
Data Index: 5941070 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0622. Min Act: -0.1700
Data Index: 103967 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0622. Min Act: -0.1700
Data Index: 1463077 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0622. Min Act: -0.1700
Data Index: 1444881 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0622. Min Act: -0.1697
Data Index: 7918032 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0622. Min Act: -0.1700
Data Index: 1606757 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0622. Min Act: -0.1700
Data Index: 7685824 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1699
Data Index: 5884084 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0309. Min Act: -0.1700
Data Index: 3719134 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0309. Min Act: -0.1700
Data Index: 5971328 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1700
Data Index: 1012526 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2184. Min Range: -6.2184
Max Act: 6.0309. Min Act: -0.1700
Data Index: 7977148 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1700
Data Index: 298361 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1700
Data Index: 49646 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1700
Data Index: 1713641 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1700
Data Index: 2070539 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2184. Min Range: -6.2184
Max Act: 5.9997. Min Act: -0.1700
Data Index: 4301758 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19