Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4676 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.5156. Min Act: -0.1700
Data Index: 7657140 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.3593. Min Act: -0.1700
Data Index: 2664842 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.3281. Min Act: -0.1700
Data Index: 3396118 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2968. Min Act: -0.1700
Data Index: 4661352 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.3281. Min Act: -0.1700
Data Index: 6481268 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2656. Min Act: -0.1700
Data Index: 337965 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2343. Min Act: -0.1700
Data Index: 4375388 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2343. Min Act: -0.1700
Data Index: 8471626 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2343. Min Act: -0.1700
Data Index: 3605840 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2656. Min Act: -0.1700
Data Index: 7656654 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2656. Min Act: -0.1700
Data Index: 6249581 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.2031. Min Act: -0.1700
Data Index: 5793919 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1718. Min Act: -0.1700
Data Index: 6604762 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1718. Min Act: -0.1700
Data Index: 102035 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1718. Min Act: -0.1700
Data Index: 7272361 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1406. Min Act: -0.1700
Data Index: 6681144 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1406. Min Act: -0.1700
Data Index: 8063935 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1406. Min Act: -0.1700
Data Index: 8678063 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1093. Min Act: -0.1700
Data Index: 1477497 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5156. Min Range: -4.5156
Max Act: 4.1093. Min Act: -0.1700
Data Index: 6775164 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19