Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2624 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.9032. Min Act: -0.1700
Data Index: 1147979 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7470. Min Act: -0.1700
Data Index: 8391809 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7157. Min Act: -0.1700
Data Index: 1203078 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7157. Min Act: -0.1700
Data Index: 524889 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7157. Min Act: -0.1700
Data Index: 7266972 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.6220. Min Act: -0.1700
Data Index: 5461877 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5595. Min Act: -0.1700
Data Index: 4877333 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5595. Min Act: -0.1700
Data Index: 5498210 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5595. Min Act: -0.1700
Data Index: 640197 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5595. Min Act: -0.1700
Data Index: 3240241 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5282. Min Act: -0.1700
Data Index: 735863 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5282. Min Act: -0.1700
Data Index: 7098883 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.5282. Min Act: -0.1700
Data Index: 2192157 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.4970. Min Act: -0.1700
Data Index: 4356365 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.4657. Min Act: -0.1700
Data Index: 5332111 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.4345. Min Act: -0.1700
Data Index: 4534700 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.4032. Min Act: -0.1700
Data Index: 6969120 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.3720. Min Act: -0.1700
Data Index: 7869465 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.3720. Min Act: -0.1700
Data Index: 458753 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.3720. Min Act: -0.1700
Data Index: 2241192 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19