Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.8190. Min Act: -0.1700
Data Index: 5523165 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.7095. Min Act: -0.1700
Data Index: 7256582 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.7095. Min Act: -0.1700
Data Index: 4494659 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6782. Min Act: -0.1700
Data Index: 8771595 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6626. Min Act: -0.1700
Data Index: 7663156 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6626. Min Act: -0.1700
Data Index: 1093826 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6470. Min Act: -0.1700
Data Index: 7738849 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6313. Min Act: -0.1700
Data Index: 7785715 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6313. Min Act: -0.1700
Data Index: 3977069 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6157. Min Act: -0.1700
Data Index: 7738848 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6000. Min Act: -0.1700
Data Index: 4551457 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5844. Min Act: -0.1700
Data Index: 7113629 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5844. Min Act: -0.1700
Data Index: 4915499 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6000. Min Act: -0.1700
Data Index: 4992134 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5687. Min Act: -0.1700
Data Index: 8290257 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5687. Min Act: -0.1700
Data Index: 57193 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5530. Min Act: -0.1700
Data Index: 2930758 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5687. Min Act: -0.1700
Data Index: 8341607 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5530. Min Act: -0.1700
Data Index: 7620198 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5530. Min Act: -0.1700
Data Index: 8341606 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19