Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.5167. Min Act: -0.1700
Data Index: 6748244 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.3292. Min Act: -0.1700
Data Index: 2654091 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.3292. Min Act: -0.1700
Data Index: 6748240 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.3292. Min Act: -0.1700
Data Index: 2707770 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2667. Min Act: -0.1700
Data Index: 6435331 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2667. Min Act: -0.1700
Data Index: 2840075 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2667. Min Act: -0.1700
Data Index: 2840074 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2667. Min Act: -0.1700
Data Index: 2795262 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2667. Min Act: -0.1700
Data Index: 6112547 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2042. Min Act: -0.1700
Data Index: 2654090 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2042. Min Act: -0.1700
Data Index: 1048138 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.1417. Min Act: -0.1700
Data Index: 4846993 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2042. Min Act: -0.1700
Data Index: 7916246 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2042. Min Act: -0.1700
Data Index: 2654065 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2042. Min Act: -0.1700
Data Index: 2654075 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2667. Min Act: -0.1700
Data Index: 2654083 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.2042. Min Act: -0.1700
Data Index: 3112883 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.1417. Min Act: -0.1700
Data Index: 2654068 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.1417. Min Act: -0.1700
Data Index: 2840072 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5167. Min Range: -10.5167
Max Act: 10.1417. Min Act: -0.1700
Data Index: 3457876 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19