Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.7693. Min Act: -0.1700
Data Index: 7085097 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.6755. Min Act: -0.1700
Data Index: 7085098 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.6755. Min Act: -0.1700
Data Index: 8286188 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.6755. Min Act: -0.1700
Data Index: 3752098 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.6755. Min Act: -0.1700
Data Index: 2863698 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.6129. Min Act: -0.1700
Data Index: 1635328 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.6129. Min Act: -0.1700
Data Index: 8311066 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5816. Min Act: -0.1700
Data Index: 3897542 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5816. Min Act: -0.1700
Data Index: 4385228 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5503. Min Act: -0.1700
Data Index: 7972114 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5503. Min Act: -0.1700
Data Index: 7431455 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5503. Min Act: -0.1700
Data Index: 2489297 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5503. Min Act: -0.1700
Data Index: 6240367 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5190. Min Act: -0.1700
Data Index: 7151109 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5190. Min Act: -0.1700
Data Index: 4396445 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5033. Min Act: -0.1700
Data Index: 3876585 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.4876. Min Act: -0.1700
Data Index: 635775 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.5033. Min Act: -0.1700
Data Index: 1344515 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.4876. Min Act: -0.1700
Data Index: 7453917 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7693. Min Range: -3.7693
Max Act: 3.4720. Min Act: -0.1700
Data Index: 6601657 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19