Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 93 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.9238. Min Act: -0.1700
Data Index: 1830577 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.8926. Min Act: -0.1700
Data Index: 7173626 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.7363. Min Act: -0.1700
Data Index: 177023 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.7051. Min Act: -0.1700
Data Index: 7454433 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.6738. Min Act: -0.1700
Data Index: 1772658 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.6738. Min Act: -0.1700
Data Index: 1191177 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.6426. Min Act: -0.1700
Data Index: 2836617 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.6113. Min Act: -0.1700
Data Index: 526177 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.6113. Min Act: -0.1700
Data Index: 4864114 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4325128 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7631668 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5488. Min Act: -0.1700
Data Index: 4415389 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5488. Min Act: -0.1700
Data Index: 1991853 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5488. Min Act: -0.1700
Data Index: 3941163 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5488. Min Act: -0.1700
Data Index: 4033955 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1414685 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.4863. Min Act: -0.1700
Data Index: 3908620 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.4863. Min Act: -0.1700
Data Index: 276877 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.4863. Min Act: -0.1700
Data Index: 7159424 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9238. Min Range: -5.9238
Max Act: 5.4863. Min Act: -0.1700
Data Index: 4518547 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19