Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.8606. Min Act: -0.1700
Data Index: 548689 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.5164. Min Act: -0.1700
Data Index: 7513015 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.5320. Min Act: -0.1700
Data Index: 3262074 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.4851. Min Act: -0.1700
Data Index: 8440163 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.4224. Min Act: -0.1700
Data Index: 567122 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.3910. Min Act: -0.1700
Data Index: 8104984 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.4067. Min Act: -0.1700
Data Index: 1092925 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.3753. Min Act: -0.1700
Data Index: 1878260 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.3283. Min Act: -0.1700
Data Index: 1328112 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2969. Min Act: -0.1700
Data Index: 8106030 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2655. Min Act: -0.1700
Data Index: 7588456 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2498. Min Act: -0.1700
Data Index: 4716592 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2183. Min Act: -0.1700
Data Index: 8812288 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2026. Min Act: -0.1700
Data Index: 4002006 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2183. Min Act: -0.1700
Data Index: 374191 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2183. Min Act: -0.1700
Data Index: 3959390 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2341. Min Act: -0.1700
Data Index: 7203044 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2183. Min Act: -0.1700
Data Index: 6029158 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.1869. Min Act: -0.1700
Data Index: 881310 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8606. Min Range: -3.8606
Max Act: 3.2183. Min Act: -0.1700
Data Index: 6861815 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19