Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3168. Min Range: -8.3168
Max Act: 8.3168. Min Act: -0.1700
Data Index: 2915274 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.9418. Min Act: -0.1700
Data Index: 6784841 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.8793. Min Act: -0.1700
Data Index: 6784842 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.8168. Min Act: -0.1700
Data Index: 1765684 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.7543. Min Act: -0.1700
Data Index: 1251076 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.4105. Min Act: -0.1700
Data Index: 721548 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.4105. Min Act: -0.1700
Data Index: 5121068 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.4105. Min Act: -0.1700
Data Index: 7294182 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.3793. Min Act: -0.1700
Data Index: 8064420 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.3793. Min Act: -0.1700
Data Index: 5323446 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.3168. Min Act: -0.1700
Data Index: 4059184 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.2855. Min Act: -0.1700
Data Index: 7308801 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.2543. Min Act: -0.1700
Data Index: 4415140 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.2230. Min Act: -0.1700
Data Index: 2806238 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.2230. Min Act: -0.1700
Data Index: 8820198 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.1918. Min Act: -0.1700
Data Index: 1939414 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.1605. Min Act: -0.1700
Data Index: 3130138 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.1293. Min Act: -0.1700
Data Index: 3049080 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.0980. Min Act: -0.1700
Data Index: 865951 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3168. Min Range: -8.3168
Max Act: 7.0355. Min Act: -0.1700
Data Index: 8064488 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19