Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1674 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.6167. Min Act: -0.1700
Data Index: 7514917 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.5541. Min Act: -0.1700
Data Index: 7514909 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.4601. Min Act: -0.1700
Data Index: 5944146 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.4444. Min Act: -0.1700
Data Index: 7514935 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.4131. Min Act: -0.1700
Data Index: 8557811 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.4131. Min Act: -0.1700
Data Index: 7514920 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.3974. Min Act: -0.1699
Data Index: 2432891 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.3504. Min Act: -0.1700
Data Index: 8683349 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.3190. Min Act: -0.1700
Data Index: 8133249 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.3190. Min Act: -0.1700
Data Index: 1168727 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.3190. Min Act: -0.1700
Data Index: 83262 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2719. Min Act: -0.1700
Data Index: 2722212 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2719. Min Act: -0.1700
Data Index: 8477112 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2719. Min Act: -0.1700
Data Index: 7514921 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2405. Min Act: -0.1700
Data Index: 7151353 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2405. Min Act: -0.1700
Data Index: 1869703 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2248. Min Act: -0.1700
Data Index: 2270768 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2090. Min Act: -0.1700
Data Index: 2739943 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2248. Min Act: -0.1700
Data Index: 7514919 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6167. Min Range: -3.6167
Max Act: 3.2090. Min Act: -0.1700
Data Index: 6084744 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19