Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.9189. Min Act: -0.1700
Data Index: 4314831 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.8408. Min Act: -0.1700
Data Index: 5650820 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.8408. Min Act: -0.1700
Data Index: 2581103 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.8095. Min Act: -0.1700
Data Index: 530253 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.7626. Min Act: -0.1700
Data Index: 1437433 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.7626. Min Act: -0.1700
Data Index: 2595784 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.7157. Min Act: -0.1700
Data Index: 5087066 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.7469. Min Act: -0.1700
Data Index: 5986246 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.7157. Min Act: -0.1700
Data Index: 5650828 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6844. Min Act: -0.1700
Data Index: 5038732 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6844. Min Act: -0.1700
Data Index: 1031951 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6844. Min Act: -0.1700
Data Index: 3081949 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6844. Min Act: -0.1700
Data Index: 7233365 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.7000. Min Act: -0.1700
Data Index: 5844546 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6687. Min Act: -0.1700
Data Index: 391291 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6687. Min Act: -0.1700
Data Index: 6195195 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6218. Min Act: -0.1700
Data Index: 8402849 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6218. Min Act: -0.1700
Data Index: 8638848 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6218. Min Act: -0.1700
Data Index: 5650827 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9189. Min Range: -3.9189
Max Act: 3.6061. Min Act: -0.1700
Data Index: 8224804 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19